Triple

T20955203
Position Surface form Disambiguated ID Type / Status
Subject Terra Sonâmbula E516081 entity
Predicate hasCharacter P2308 FINISHED
Object Tuahir
Tuahir is a wise, elderly wanderer who serves as a mentor and protector to the boy Muidinga in Mia Couto’s novel "Terra Sonâmbula."
 E1459584 NE FINISHED

How this triple was built (4 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: Tuahir | Statement: [Terra Sonâmbula, hasCharacter, Tuahir]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Tuahir
Context triple: [Terra Sonâmbula, hasCharacter, Tuahir]
  • A. Derabish
    Derabish is a town and administrative block in the Kendrapara district of the Indian state of Odisha.
  • B. Sulem
    Sulem is a modern locality believed by some scholars to correspond to the ancient biblical town of Shunem in present-day Israel.
  • C. Nadera
    Nadera is a suburban locality within the greater Suva–Nausori urban region in Fiji.
  • D. Yetûr
    Yetûr is a transliterated form of the biblical name Jetur, one of the descendants of Ishmael mentioned in the Hebrew Bible.
  • E. Akhras
    Akhras is a Syrian-origin family name best known for being the maiden surname of Asma al-Assad, the First Lady of Syria.
  • 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: Tuahir
Triple: [Terra Sonâmbula, hasCharacter, Tuahir]
Generated description
Tuahir is a wise, elderly wanderer who serves as a mentor and protector to the boy Muidinga in Mia Couto’s novel "Terra Sonâmbula."
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Tuahir
Target entity description: Tuahir is a wise, elderly wanderer who serves as a mentor and protector to the boy Muidinga in Mia Couto’s novel "Terra Sonâmbula."
  • A. Derabish
    Derabish is a town and administrative block in the Kendrapara district of the Indian state of Odisha.
  • B. Sulem
    Sulem is a modern locality believed by some scholars to correspond to the ancient biblical town of Shunem in present-day Israel.
  • C. Nadera
    Nadera is a suburban locality within the greater Suva–Nausori urban region in Fiji.
  • D. Yetûr
    Yetûr is a transliterated form of the biblical name Jetur, one of the descendants of Ishmael mentioned in the Hebrew Bible.
  • E. Akhras
    Akhras is a Syrian-origin family name best known for being the maiden surname of Asma al-Assad, the First Lady of Syria.
  • F. None of above. chosen

Provenance (5 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_69e0b4fcd678819087a304291f14330a completed April 16, 2026, 10:07 a.m.
NER Named-entity recognition batch_69e6fae2299c8190afa1b9ec5bd9df32 completed April 21, 2026, 4:19 a.m.
NED1 Entity disambiguation (via context triple) batch_6a092794c7d08190a2b8146a2379b7bd completed May 17, 2026, 2:27 a.m.
NEDg Description generation batch_6a0928b4be448190bd862c8f971e61d9 completed May 17, 2026, 2:32 a.m.
NED2 Entity disambiguation (via description) batch_6a0929734a5c8190911e54b601118bae completed May 17, 2026, 2:35 a.m.
Created at: April 16, 2026, 1:28 p.m.