Triple

T5469118
Position Surface form Disambiguated ID Type / Status
Subject United College E122786 entity
Predicate locatedIn P40 FINISHED
Object St Andrews E14531 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: St Andrews | Statement: [United College, locatedIn, St Andrews]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: St Andrews
Context triple: [United College, locatedIn, St Andrews]
  • A. St Andrews chosen
    St Andrews is a historic coastal town in eastern Scotland renowned for its ancient university and status as the "home of golf."
  • B. Stirling
    Stirling is a historic Scottish city known for its medieval castle, strategic location, and role in key battles such as Stirling Bridge and Bannockburn.
  • C. Stirling
    Stirling is a picturesque town in the Adelaide Hills region of South Australia, known for its leafy streets, cool-climate gardens, and historic charm.
  • D. Dunfermline
    Dunfermline is a historic Scottish town and former royal capital known for its medieval abbey and rich cultural heritage.
  • E. Balerno
    Balerno is a suburban village on the outskirts of Edinburgh, Scotland, known for its scenic setting near the Pentland Hills and its residential 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_69bd46459ff48190823377457bcf7128 completed March 20, 2026, 1:06 p.m.
NER Named-entity recognition batch_69bd92198ea08190a08357f3756572a2 completed March 20, 2026, 6:29 p.m.
NED1 Entity disambiguation (via context triple) batch_69bf4893029081908a801c7a44872ebf completed March 22, 2026, 1:40 a.m.
Created at: March 20, 2026, 2:09 p.m.