Triple

T18086389
Position Surface form Disambiguated ID Type / Status
Subject Maria of Mangup E432844 entity
Predicate placeOfOrigin P3743 FINISHED
Object Mangup
Mangup is a historic fortress town in Crimea, known as the medieval capital of the Principality of Theodoro and a significant stronghold in the region.
 E1306022 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: Mangup | Statement: [Maria of Mangup, placeOfOrigin, Mangup]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Mangup
Context triple: [Maria of Mangup, placeOfOrigin, Mangup]
  • A. Mangin
    Mangin is a French surname borne by various notable figures, including military leaders, politicians, and artists.
  • B. Mangseng
    Mangseng is an Oceanic language spoken in parts of western Melanesia, belonging to the Western Oceanic branch of the Austronesian language family.
  • C. Mupun
    Mupun is a West Chadic language spoken primarily in central Nigeria by the Mupun people.
  • D. Manghit
    Manghit was a Central Asian tribal group that rose to prominence as the ruling clan of the Manghit (Bukhara) dynasty.
  • E. Mangano
    Mangano is an Italian surname most famously associated with actress Silvana Mangano, a prominent figure in mid-20th-century Italian cinema.
  • 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: Mangup
Triple: [Maria of Mangup, placeOfOrigin, Mangup]
Generated description
Mangup is a historic fortress town in Crimea, known as the medieval capital of the Principality of Theodoro and a significant stronghold in the region.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Mangup
Target entity description: Mangup is a historic fortress town in Crimea, known as the medieval capital of the Principality of Theodoro and a significant stronghold in the region.
  • A. Mangin
    Mangin is a French surname borne by various notable figures, including military leaders, politicians, and artists.
  • B. Mangseng
    Mangseng is an Oceanic language spoken in parts of western Melanesia, belonging to the Western Oceanic branch of the Austronesian language family.
  • C. Mupun
    Mupun is a West Chadic language spoken primarily in central Nigeria by the Mupun people.
  • D. Manghit
    Manghit was a Central Asian tribal group that rose to prominence as the ruling clan of the Manghit (Bukhara) dynasty.
  • E. Mangano
    Mangano is an Italian surname most famously associated with actress Silvana Mangano, a prominent figure in mid-20th-century Italian cinema.
  • 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_69d8b907d05c819083cc3bd6021089e6 completed April 10, 2026, 8:47 a.m.
NER Named-entity recognition batch_69e4dd150ab88190864be2a722d214b8 completed April 19, 2026, 1:48 p.m.
NED1 Entity disambiguation (via context triple) batch_6a035d97912c8190b5d281ddd08de4f1 completed May 12, 2026, 5:04 p.m.
NEDg Description generation batch_6a036e9077308190be6e7d228dcf11b4 completed May 12, 2026, 6:16 p.m.
NED2 Entity disambiguation (via description) batch_6a03795b255c8190a84ca0ce2fda4599 completed May 12, 2026, 7:02 p.m.
Created at: April 10, 2026, 10:27 a.m.