Triple

T9648660
Position Surface form Disambiguated ID Type / Status
Subject Paul Givan E233274 entity
Predicate work location P1527 FINISHED
Object Stormont E791424 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: Stormont | Statement: [Paul Givan, work location, Stormont]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Stormont
Context triple: [Paul Givan, work location, Stormont]
  • A. Stormont chosen
    Stormont is the hill and parliamentary estate in Belfast that houses the Northern Ireland Assembly and key government buildings.
  • B. Stormont
    Stormont is a historic county in eastern Ontario, Canada, now part of the United Counties of Stormont, Dundas and Glengarry.
  • C. North Stormont
    North Stormont is a rural township in eastern Ontario, Canada, known for its agricultural landscape and small communities within the former Stormont County.
  • D. South Stormont
    South Stormont is a rural township in eastern Ontario, Canada, known for its agricultural communities and location along the St. Lawrence River.
  • E. Lord Stormont
    Lord Stormont was an 18th-century British diplomat and politician who served in several high-ranking governmental and ambassadorial roles under King George III.
  • 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_69ca848b31648190b57aa55da20285be completed March 30, 2026, 2:11 p.m.
NER Named-entity recognition batch_69cd9bac55b48190ab2a8f9bb83c951e completed April 1, 2026, 10:26 p.m.
NED1 Entity disambiguation (via context triple) batch_69d18262dc50819089cfc17c770a1a90 completed April 4, 2026, 9:28 p.m.
Created at: March 30, 2026, 8:13 p.m.