Triple

T12347272
Position Surface form Disambiguated ID Type / Status
Subject Union School E294388 entity
Predicate name P16 FINISHED
Object Union School E294388 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: Union School | Statement: [Union School, name, Union School]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Union School
Context triple: [Union School, name, Union School]
  • A. Union School chosen
    Union School is a public elementary school serving students in the town of Farmington, Connecticut.
  • B. Runkle School
    Runkle School is a public K–8 elementary school located in Brookline, Massachusetts, serving students in the local community as part of the town’s public school system.
  • C. Union High School
    Union High School is a public secondary school serving students in and around La Porte City, Iowa.
  • D. Union High School
    Union High School is an American secondary school best known as the alma mater of actor Ray Liotta.
  • E. Union High School
    Union High School is an American secondary school best known as the alma mater of actor and comedian Robert Wuhl.
  • 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_69d6ab6ccbec8190b09e2d357aa80064 completed April 8, 2026, 7:24 p.m.
NER Named-entity recognition batch_69d93f7ba17481908b03af7316b28d9b completed April 10, 2026, 6:20 p.m.
NED1 Entity disambiguation (via context triple) batch_69f64b90779881909893d1e6877ce567 completed May 2, 2026, 7:08 p.m.
Created at: April 8, 2026, 9:53 p.m.