Triple

T15905454
Position Surface form Disambiguated ID Type / Status
Subject Amy Sedaris E385699 entity
Predicate hasCollaboratedWith P8554 FINISHED
Object Stephen Colbert E105911 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: Stephen Colbert | Statement: [Amy Sedaris, hasCollaboratedWith, Stephen Colbert]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Stephen Colbert
Context triple: [Amy Sedaris, hasCollaboratedWith, Stephen Colbert]
  • A. Stephen Colbert chosen
    Stephen Colbert is an American comedian, writer, producer, political satirist, and television host best known for his work on "The Colbert Report" and "The Late Show with Stephen Colbert."
  • B. Con Colbert
    Con Colbert was an Irish republican and member of the Irish Volunteers who played a key role in the 1916 Easter Rising and was executed for his involvement.
  • C. Colbert
    Colbert is a prominent restaurant in London known for its Parisian-style café atmosphere and classic French brasserie cuisine.
  • D. Colbert
    Colbert is a French surname most famously associated with Jean-Baptiste Colbert, the influential 17th-century statesman who served as finance minister under King Louis XIV.
  • E. Jon Stewart
    Jon Stewart is an American comedian, writer, producer, and former host of "The Daily Show," widely known for his sharp political satire and influence on contemporary news comedy.
  • 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_69d86da686e4819097cbf3b1fc2d881d completed April 10, 2026, 3:25 a.m.
NER Named-entity recognition batch_69e1565956588190ba4726a2879b677d completed April 16, 2026, 9:36 p.m.
NED1 Entity disambiguation (via context triple) batch_69ffb0535a808190983b4ff028826cbf completed May 9, 2026, 10:08 p.m.
Created at: April 10, 2026, 4:52 a.m.