Triple

T14173942
Position Surface form Disambiguated ID Type / Status
Subject The War Lord E351283 entity
Predicate starring P1507 FINISHED
Object Michael Conrad E269486 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 Conrad | Statement: [The War Lord, starring, Michael Conrad]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Michael Conrad
Context triple: [The War Lord, starring, Michael Conrad]
  • A. Michael Conrad chosen
    Michael Conrad was an American character actor best known for his Emmy-winning role as Sgt. Phil Esterhaus on the television series "Hill Street Blues."
  • B. James Conrad
    James Conrad is a skilled former British Special Air Service captain who serves as a tracker and guide for the expedition to Skull Island in the film "Kong: Skull Island" within the King Kong franchise.
  • C. Chris Conrad
    Chris Conrad is an American actor known for his roles in 1990s action and comedy films and various television series.
  • D. Chris Conrad
    Chris Conrad is a writer known for his work at the junior level, contributing developing written content and honing his craft.
  • E. Michael Condrey
    Michael Condrey is a video game developer best known as the co-founder of Sledgehammer Games and for his work on the Call of Duty franchise.
  • 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_69d8278834a08190b0f1784e58d7b99c completed April 9, 2026, 10:26 p.m.
NER Named-entity recognition batch_69de61b7cc3081909f4fa371e1eae130 completed April 14, 2026, 3:48 p.m.
NED1 Entity disambiguation (via context triple) batch_69fcf80a9b34819081c4ebf7429e875a completed May 7, 2026, 8:37 p.m.
Created at: April 10, 2026, 1:01 a.m.