Triple

T5078805
Position Surface form Disambiguated ID Type / Status
Subject Third Court, Jesus College, Cambridge E114462 entity
Predicate hasName P744 FINISHED
Object Third Court E114462 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: Third Court | Statement: [Third Court, Jesus College, Cambridge, hasName, Third Court]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Third Court
Context triple: [Third Court, Jesus College, Cambridge, hasName, Third Court]
  • A. Third Court chosen
    Third Court is a historic quadrangle within Jesus College, Cambridge, known for its traditional collegiate architecture and central role in college life.
  • B. Third Court
    Third Court is one of the main quadrangles of Magdalene College, Cambridge, forming part of its historic collegiate layout.
  • C. Third Court
    Third Court is one of the historic courtyards of Christ's College, Cambridge, forming part of the college's traditional architectural layout and communal space.
  • D. Third Court
    Third Court is one of the historic quadrangles of St John’s College, Cambridge, known for its traditional collegiate architecture and role in the daily life of the college.
  • E. Second Court
    Second Court is one of the main historic courtyards of Jesus College, Cambridge, around which several of the college’s key buildings are arranged.
  • 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_69bd443dbf908190a9401e9c2dc7bd7d completed March 20, 2026, 12:57 p.m.
NER Named-entity recognition batch_69bd74f75cf0819088be9e076eaf3168 completed March 20, 2026, 4:25 p.m.
NED1 Entity disambiguation (via context triple) batch_69beb12bd7288190b66ac606aebcabca completed March 21, 2026, 2:54 p.m.
Created at: March 20, 2026, 1:39 p.m.