Triple

T17818492
Position Surface form Disambiguated ID Type / Status
Subject Ross and Cromarty E444909 entity
Predicate contains P35 FINISHED
Object Fortrose 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: Fortrose | Statement: [Ross and Cromarty, contains, Fortrose]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Fortrose
Context triple: [Ross and Cromarty, contains, Fortrose]
  • A. Fortrose chosen
    Fortrose is a historic coastal town on the Black Isle in the Scottish Highlands, noted for its medieval cathedral ruins and scenic views over the Moray Firth.
  • B. Corsicana
    Corsicana is a small city in north-central Texas known for its oil boom history and as a regional commercial and transportation hub between Dallas and Houston.
  • C. Crosbyton
    Crosbyton is a small rural city in West Texas that serves as the administrative and commercial hub of Crosby County.
  • D. Stephenville
    Stephenville is a town on the west coast of Newfoundland, Canada, known historically for its former U.S. air force base and its role as a regional service and transportation hub.
  • E. Beeville
    Beeville is a small city in southern Texas known as the county seat of Bee County and home to Coastal Bend College.
  • 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_69d8b9f0de78819099395b14db75a8a6 completed April 10, 2026, 8:50 a.m.
NER Named-entity recognition batch_69e488812df081909771d51c54c405fe completed April 19, 2026, 7:47 a.m.
Created at: April 10, 2026, 10:14 a.m.