Triple

T12917145
Position Surface form Disambiguated ID Type / Status
Subject Marilu Henner E309013 entity
Predicate spouse P13 FINISHED
Object Michael Brown E977836 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: Michael Brown | Statement: [Marilu Henner, spouse, Michael Brown]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Michael Brown
Context triple: [Marilu Henner, spouse, Michael Brown]
  • A. Michael Brown
    Michael Brown is an American actor better known professionally as Michael Ealy, recognized for his roles in films like "Barbershop" and "Think Like a Man" and the TV series "Almost Human."
  • B. Michael Brown chosen
    Michael Brown is an American songwriter and keyboardist best known as a founding member of the baroque pop band The Left Banke and writer of several of its hit songs.
  • C. Michael Brown
    Michael Brown is a film and television editor known for his work on the biographical miniseries "Life with Judy Garland: Me and My Shadows."
  • D. Michael Brown
    Michael Brown is a musician best known as a member of the indie supergroup Gayngs.
  • E. Travon Potts
    Travon Potts is an American songwriter and producer known for his work in R&B and pop music, contributing to songs for artists such as Monica and Christina Aguilera.
  • 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_69d7bdf92b588190acdf2a2291ac4590 completed April 9, 2026, 2:55 p.m.
NER Named-entity recognition batch_69d971a1e8088190af697629baecf59f completed April 10, 2026, 9:54 p.m.
NED1 Entity disambiguation (via context triple) batch_69f6a571a3e48190a32d362adc6eaee2 completed May 3, 2026, 1:31 a.m.
Created at: April 9, 2026, 5:41 p.m.