Triple

T19627771
Position Surface form Disambiguated ID Type / Status
Subject Broken Arrow E471182 entity
Predicate stars P1956 FINISHED
Object Delroy Lindo NE NERFINISHED

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: Delroy Lindo | Statement: [Broken Arrow, stars, Delroy Lindo]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Delroy Lindo
Context triple: [Broken Arrow, stars, Delroy Lindo]
  • A. Delroy Lindo chosen
    Delroy Lindo is a British-American actor acclaimed for his powerful performances in film, television, and theater, particularly in collaborations with director Spike Lee.
  • B. Keith David Williams
    Keith David Williams, known professionally as Keith David, is an American actor and voice actor renowned for his deep, resonant voice and roles in films like "The Thing," "They Live," and numerous animated and video game projects.
  • C. Denzil Franco
    Denzil Franco is an Indian professional footballer known for playing as a defender in the I-League and Indian Super League, as well as representing the Indian national team.
  • D. Marlon Young
    Marlon Young is a music producer best known for his work on Greta Van Fleet’s breakout EP "Black Smoke Rising."
  • E. Terrence Stamp
    Terrence Stamp is an English actor known for his distinctive presence and roles in films such as "The Collector," "Superman II," and "The Limey."
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69d8e511f28481909f4bc3ea9191e54a completed April 10, 2026, 11:54 a.m.
NER Named-entity recognition batch_69e640eadcc48190ab5e36ddcde0c328 completed April 20, 2026, 3:06 p.m.
Created at: April 10, 2026, 1:44 p.m.