Triple

T10650575
Position Surface form Disambiguated ID Type / Status
Subject Troy Kennedy Martin E250955 entity
Predicate placeOfDeath P21 FINISHED
Object Dromara E565582 NE FINISHED

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: Dromara | Statement: [Troy Kennedy Martin, placeOfDeath, Dromara]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Dromara
Context triple: [Troy Kennedy Martin, placeOfDeath, Dromara]
  • A. Dromara chosen
    Dromara is a small village in County Down, Northern Ireland, known for its rural setting near the Slieve Croob hills.
  • B. Dromi
    Dromi is a mythical chain in Norse mythology that was used in an early attempt to bind the monstrous wolf Fenrir.
  • C. Dramaga
    Dramaga is a district in West Java, Indonesia, known for hosting the main campus of Bogor Agricultural University (IPB) and forming part of the greater Bogor area.
  • D. Droshak
    Droshak is the official newspaper and central publication of the Armenian Revolutionary Federation, serving as a key organ for its political views and party news.
  • E. Damastes
    Damastes is a figure from Greek mythology better known by the epithet Procrustes, a bandit infamous for violently stretching or cutting his victims to make them fit an iron bed.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69d6aa5a4c4881908f39be6efe5981e5 completed April 8, 2026, 7:19 p.m.
NER Named-entity recognition batch_69d6dfe4b97081908815b77612222318 completed April 8, 2026, 11:08 p.m.
NED1 Entity disambiguation (via context triple) batch_69d97a69a57c81908bf99cac0c0a49f2 completed April 10, 2026, 10:32 p.m.
Created at: April 8, 2026, 9:06 p.m.