Triple

T2718399
Position Surface form Disambiguated ID Type / Status
Subject MIT Recreation E60021 entity
Predicate hasFacility P105 FINISHED
Object Rockwell Cage E208 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: Rockwell Cage | Statement: [MIT Recreation, hasFacility, Rockwell Cage]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Rockwell Cage
Context triple: [MIT Recreation, hasFacility, Rockwell Cage]
  • A. Rockwell Cage chosen
    Rockwell Cage is an indoor athletic facility at the Massachusetts Institute of Technology that serves as the primary venue for the MIT Engineers’ home sports events.
  • B. Russell Vought
    Russell Vought is an American political operative and policy advisor who served as Director of the Office of Management and Budget under President Donald Trump.
  • C. Carl Ellsworth
    Carl Ellsworth is an American screenwriter known for writing suspense and thriller films such as "Red Eye" and "Disturbia."
  • D. Michael Sidney Luft
    Michael Sidney Luft was an American show business figure best known as a film producer and the third husband and manager of entertainer Judy Garland.
  • E. Skip Woods
    Skip Woods is an American screenwriter and film producer known for writing action films such as "Swordfish," "Hitman," and "A Good Day to Die Hard."
  • 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_69ab4b746d248190958e052045c09255 completed March 6, 2026, 9:47 p.m.
NER Named-entity recognition batch_69abdaad577c8190819d3c641c2406f4 completed March 7, 2026, 7:58 a.m.
NED1 Entity disambiguation (via context triple) batch_69afb68ebd0081908bb360872d559e1f completed March 10, 2026, 6:13 a.m.
Created at: March 6, 2026, 9:55 p.m.