Triple

T5100306
Position Surface form Disambiguated ID Type / Status
Subject Down E114965 entity
Predicate contains P35 FINISHED
Object Holywood E402673 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: Holywood | Statement: [Down, contains, Holywood]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Holywood
Context triple: [Down, contains, Holywood]
  • A. Holywood chosen
    Holywood is a coastal town in County Down, Northern Ireland, situated on the shores of Belfast Lough and known for its historic churches and affluent residential character.
  • B. Holybourne
    Holybourne is a small village in Hampshire, England, situated just outside the market town of Alton.
  • C. Guildwood
    Guildwood is a residential lakeside neighbourhood in the eastern part of Toronto, Ontario, known for its scenic bluffs, parkland, and planned community layout.
  • D. Bordon
    Bordon is a town in East Hampshire, England, historically known for its large army camp and military training facilities.
  • E. Stonehouse
    Stonehouse is a village in South Lanarkshire, Scotland, known for its historic conservation area and rural character.
  • 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_69bd443fc49c819089629c00e311310c completed March 20, 2026, 12:57 p.m.
NER Named-entity recognition batch_69bd758381dc8190ac491788d27ab8e0 completed March 20, 2026, 4:27 p.m.
NED1 Entity disambiguation (via context triple) batch_69beba8977f481908b0d55a9cd28d492 completed March 21, 2026, 3:34 p.m.
Created at: March 20, 2026, 1:40 p.m.