Triple

T13989069
Position Surface form Disambiguated ID Type / Status
Subject Terry Malloy E336518 entity
Predicate enemy P4567 FINISHED
Object Johnny Friendly E943806 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: Johnny Friendly | Statement: [Terry Malloy, enemy, Johnny Friendly]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Johnny Friendly
Context triple: [Terry Malloy, enemy, Johnny Friendly]
  • A. Johnny Friendly chosen
    Johnny Friendly is the corrupt and ruthless mob-connected union boss who serves as the main antagonist in the classic film "On the Waterfront."
  • B. Officer Bill Lockwood
    Officer Bill Lockwood is a fictional police officer featured as a central character in the classic American radio crime drama series "Dragnet."
  • C. Stan Fink
    Stan Fink is a supporting character in the film "Eternal Sunshine of the Spotless Mind," working as a technician for the memory-erasing company Lacuna, Inc.
  • D. Joe Gage
    Joe Gage is a character in Quentin Tarantino’s film "The Hateful Eight," portrayed as a seemingly quiet cowboy whose true motives emerge amid the tense standoff in the isolated Snowbound Haberdashery.
  • E. Lester Cole
    Lester Cole was an American screenwriter and one of the Hollywood Ten, blacklisted during the Red Scare for alleged communist affiliations.
  • 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_69d81c639e808190a0e4b4f3d31c6a59 completed April 9, 2026, 9:38 p.m.
NER Named-entity recognition batch_69de2ea537408190bb9d35963886803f completed April 14, 2026, 12:10 p.m.
NED1 Entity disambiguation (via context triple) batch_69fbac9604cc819088cde0ad8271ad48 completed May 6, 2026, 9:03 p.m.
Created at: April 9, 2026, 10:18 p.m.