Triple

T21852463
Position Surface form Disambiguated ID Type / Status
Subject Red Line trunk E539537 entity
Predicate hasStation P35 FINISHED
Object Central 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: Central | Statement: [Red Line trunk, hasStation, Central]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Central
Context triple: [Red Line trunk, hasStation, Central]
  • A. Central
    Central is the standard map abbreviation used to denote the Central line, one of the primary east–west routes on the London Underground.
  • B. Central
    Central was a former local government region in Scotland that existed from 1975 to 1996, covering areas including Stirling, Falkirk, and Clackmannan.
  • C. Central
    Central is the primary public repository for Java and JVM-based libraries used by the Apache Maven build automation tool and other dependency management systems.
  • D. Central chosen
    Central is a subway station on the Massachusetts Bay Transportation Authority (MBTA) system located in Cambridge, Massachusetts.
  • E. Central
    Central is a former British ITV regional television company that served the Midlands region and produced a wide range of popular UK programming.
  • 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_69e0c47829648190bbe2d1d7033768ec completed April 16, 2026, 11:14 a.m.
NER Named-entity recognition batch_69f0bd59bcbc819093829feb152e090d completed April 28, 2026, 1:59 p.m.
Created at: April 16, 2026, 6:56 p.m.