Triple

T18086400
Position Surface form Disambiguated ID Type / Status
Subject Maria of Mangup E432844 entity
Predicate residence P75 FINISHED
Object Mangup NE NERFINISHED

How this triple was built (2 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, residence, Mangup]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mangup
Context triple: [Maria of Mangup, residence, Mangup]
  • A. Mangup chosen
    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.
  • B. Mangin
    Mangin is a French surname borne by various notable figures, including military leaders, politicians, and artists.
  • C. Mangseng
    Mangseng is an Oceanic language spoken in parts of western Melanesia, belonging to the Western Oceanic branch of the Austronesian language family.
  • D. Mupun
    Mupun is a West Chadic language spoken primarily in central Nigeria by the Mupun people.
  • E. Manghit
    Manghit was a Central Asian tribal group that rose to prominence as the ruling clan of the Manghit (Bukhara) dynasty.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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.
Created at: April 10, 2026, 10:27 a.m.