Triple

T20586078
Position Surface form Disambiguated ID Type / Status
Subject Demetrius and the Gladiators E505790 entity
Predicate producer P490 FINISHED
Object Frank Ross 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: Frank Ross | Statement: [Demetrius and the Gladiators, producer, Frank Ross]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Frank Ross
Context triple: [Demetrius and the Gladiators, producer, Frank Ross]
  • A. Frank Ross
    Frank Ross is a fictional rancher whose murder sets the revenge-driven plot in Charles Portis's novel "True Grit" into motion.
  • B. Frank Ross chosen
    Frank Ross was an American film producer known for his work on major mid-20th-century Hollywood productions.
  • C. William Ross
    William Ross is an American composer, orchestrator, and conductor known for his work on numerous film scores and collaborations with major Hollywood productions.
  • D. Charles Wood
    Charles Wood was an Irish-born composer and influential teacher associated with the English Musical Renaissance, best known for his Anglican church music and role in shaping early 20th-century British composers.
  • E. Charles Wood
    Charles Wood was a British playwright and screenwriter known for his sharp, satirical writing and influential work in film, television, and theatre.
  • 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_69e0b4b9669c8190b8e81fc72817d42c completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e6a976bca4819086a4949e299159b5 completed April 20, 2026, 10:32 p.m.
Created at: April 16, 2026, 11:40 a.m.