Triple

T20991005
Position Surface form Disambiguated ID Type / Status
Subject Stealth (2005 film) E517022 entity
Predicate mainCharacter P1183 FINISHED
Object EDI 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: EDI | Statement: [Stealth (2005 film), mainCharacter, EDI]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: EDI
Context triple: [Stealth (2005 film), mainCharacter, EDI]
  • A. EDI
    EDI is the three-letter IATA airport code for Edinburgh Airport, the main international airport serving Scotland’s capital city.
  • B. EDI chosen
    EDI is an artificial intelligence character from the Mass Effect video game series, known for her evolving personality and role as the Normandy's ship AI and later as a humanoid squadmate.
  • C. EDI
    EDI is the official abbreviation for the Swiss Federal Department of Home Affairs, a key government ministry responsible for social security, health, culture, and related domestic affairs.
  • D. IDOC
    IDOC is the state agency responsible for overseeing prisons, community-based corrections, and offender rehabilitation in Iowa.
  • E. IDOC
    IDOC is the state agency responsible for overseeing prisons, parole, and related correctional services in Illinois.
  • 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_69e0b5006e2881909fc2383f841740cc completed April 16, 2026, 10:08 a.m.
NER Named-entity recognition batch_69e6fc1ba3d0819080d9d03817a45026 completed April 21, 2026, 4:24 a.m.
Created at: April 16, 2026, 1:50 p.m.