Triple

T22050326
Position Surface form Disambiguated ID Type / Status
Subject Tangut script E544864 entity
Predicate hasNotableManuscriptCorpus P142947 FINISHED
Object Khara-Khoto manuscripts
The Khara-Khoto manuscripts are a major cache of medieval texts discovered in the ruins of the Tangut city of Khara-Khoto, providing crucial evidence for the language, religion, and culture of the Western Xia dynasty.
E1515682 NE FINISHED

How this triple was built (5 steps)

Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.

NER Named-entity recognition gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: Khara-Khoto manuscripts | Statement: [Tangut script, hasNotableManuscriptCorpus, Khara-Khoto manuscripts]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Khara-Khoto manuscripts
Context triple: [Tangut script, hasNotableManuscriptCorpus, Khara-Khoto manuscripts]
  • A. Turfan manuscripts
    The Turfan manuscripts are a significant collection of ancient Central Asian texts, preserving religious, literary, and administrative writings in multiple languages and scripts that illuminate the cultural and linguistic history of the Silk Road region.
  • B. Dunhuang manuscripts
    The Dunhuang manuscripts are a vast cache of ancient texts, paintings, and documents discovered in the Mogao Caves near Dunhuang, China, offering unparalleled insight into the religious, cultural, and social life of medieval Central and East Asia.
  • C. Chu silk manuscripts
    The Chu silk manuscripts are ancient Chinese texts from the Warring States period, written on silk and notable for their early depictions of cosmology, mythology, and divination practices.
  • D. Sand-Buried Ruins of Khotan
    Sand-Buried Ruins of Khotan is an archaeological and travel narrative by Aurel Stein detailing his explorations and discoveries of ancient sites around Khotan in the Taklamakan Desert.
  • E. Antemoro manuscripts
    The Antemoro manuscripts are a corpus of historical and esoteric texts from Madagascar, preserved by the Antemoro people and written in the Arabic-derived Sorabe script.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Khara-Khoto manuscripts
Triple: [Tangut script, hasNotableManuscriptCorpus, Khara-Khoto manuscripts]
Generated description
The Khara-Khoto manuscripts are a major cache of medieval texts discovered in the ruins of the Tangut city of Khara-Khoto, providing crucial evidence for the language, religion, and culture of the Western Xia dynasty.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Khara-Khoto manuscripts
Target entity description: The Khara-Khoto manuscripts are a major cache of medieval texts discovered in the ruins of the Tangut city of Khara-Khoto, providing crucial evidence for the language, religion, and culture of the Western Xia dynasty.
  • A. Turfan manuscripts
    The Turfan manuscripts are a significant collection of ancient Central Asian texts, preserving religious, literary, and administrative writings in multiple languages and scripts that illuminate the cultural and linguistic history of the Silk Road region.
  • B. Dunhuang manuscripts
    The Dunhuang manuscripts are a vast cache of ancient texts, paintings, and documents discovered in the Mogao Caves near Dunhuang, China, offering unparalleled insight into the religious, cultural, and social life of medieval Central and East Asia.
  • C. Chu silk manuscripts
    The Chu silk manuscripts are ancient Chinese texts from the Warring States period, written on silk and notable for their early depictions of cosmology, mythology, and divination practices.
  • D. Sand-Buried Ruins of Khotan
    Sand-Buried Ruins of Khotan is an archaeological and travel narrative by Aurel Stein detailing his explorations and discoveries of ancient sites around Khotan in the Taklamakan Desert.
  • E. Antemoro manuscripts
    The Antemoro manuscripts are a corpus of historical and esoteric texts from Madagascar, preserved by the Antemoro people and written in the Arabic-derived Sorabe script.
  • F. None of above. chosen
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: hasNotableManuscriptCorpus
Context triple: [Tangut script, hasNotableManuscriptCorpus, Khara-Khoto manuscripts]
  • A. hasNotableCorpus
    Indicates that an entity possesses a significant, well-recognized body of work, texts, or collected materials associated with it.
  • B. areManuscriptsOf
    Indicates that the subject entities are manuscripts that are versions, copies, or instances of the work represented by the object entity.
  • C. notableManuscriptSource chosen
    Indicates that one entity serves as a significant or historically important manuscript source for another entity.
  • D. hasManuscriptsIn
    Indicates that an entity possesses or is associated with manuscripts that are located in a specified place or collection.
  • E. notableManuscriptFeature
    Indicates that a manuscript possesses a specific distinguishing characteristic, attribute, or element that is considered noteworthy or significant.
  • F. None of above.

Provenance (6 batches)

The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.

Step Stage Batch ID Status When
creating Elicitation batch_69e11e32445c8190ab97089b48a130bb completed April 16, 2026, 5:36 p.m.
NER Named-entity recognition batch_69f128323fb08190b9592fd08a96cba0 completed April 28, 2026, 9:35 p.m.
NED1 Entity disambiguation (via context triple) batch_6a0a7b79594c8190b66439167d7a3cbd completed May 18, 2026, 2:37 a.m.
NEDg Description generation batch_6a0a7cb2b0c88190930290efe1d8371a completed May 18, 2026, 2:42 a.m.
NED2 Entity disambiguation (via description) batch_6a0a7e131ae48190a564a86d3d691e1a completed May 18, 2026, 2:48 a.m.
PD Predicate disambiguation batch_69e6f643ca74819083e8ab78e843f243 completed April 21, 2026, 4 a.m.
Created at: April 16, 2026, 8:26 p.m.