Triple

T15751943
Position Surface form Disambiguated ID Type / Status
Subject Tower Heist E381867 entity
Predicate starring P1507 FINISHED
Object Alan Alda E117569 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: Alan Alda | Statement: [Tower Heist, starring, Alan Alda]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Alan Alda
Context triple: [Tower Heist, starring, Alan Alda]
  • A. Alan Alda chosen
    Alan Alda is an American actor, writer, and science communicator best known for his role on the television series M*A*S*H and his work promoting public understanding of science.
  • B. Robert Alda
    Robert Alda was an American actor and singer, and the father of actor Alan Alda, known for his work in film, theater, and television from the 1940s onward.
  • C. Robert MacNeil
    Robert MacNeil is a Canadian-American journalist and author best known for co-creating and co-anchoring the long-running public television news program that became PBS NewsHour.
  • D. Antony Alda
    Antony Alda was an American actor and screenwriter, known for his work in film and television and for being part of the Alda acting family.
  • E. Leon Robbins
    Leon Robbins is a member of the Robbins family, related to filmmaker Jack Henry Robbins and part of a well-known entertainment-industry lineage.
  • 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_69d86d9e6b44819085d1f6a969ecb74c completed April 10, 2026, 3:25 a.m.
NER Named-entity recognition batch_69e05030e31081908c307a8dc7067db4 completed April 16, 2026, 2:57 a.m.
NED1 Entity disambiguation (via context triple) batch_69ff876f005c8190913dec49b839b9f9 completed May 9, 2026, 7:13 p.m.
Created at: April 10, 2026, 4:47 a.m.