Triple

T11290366
Position Surface form Disambiguated ID Type / Status
Subject John Romero E267307 entity
Predicate employer P7 FINISHED
Object id Software E52886 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: id Software | Statement: [John Romero, employer, id Software]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: id Software
Context triple: [John Romero, employer, id Software]
  • A. id Software chosen
    id Software is an American video game developer best known for pioneering the first-person shooter genre with titles like Doom and Quake.
  • B. Raven Software
    Raven Software is an American video game developer best known for its work on first-person shooters and contributions to the Call of Duty franchise.
  • C. Croteam
    Croteam is a Croatian video game development studio best known for creating fast-paced first-person shooters and the Serious Sam series.
  • D. 3D Realms
    3D Realms is a video game developer best known for creating the influential first-person shooter Duke Nukem 3D and pioneering shareware distribution in the 1990s.
  • E. Ensemble Studios
    Ensemble Studios was an American video game development company best known for creating the influential real-time strategy franchise Age of Empires.
  • 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_69d6aac993a08190a6f36445ebaf9a43 completed April 8, 2026, 7:21 p.m.
NER Named-entity recognition batch_69d7e98875a08190b8509fe55e49d52d completed April 9, 2026, 6:01 p.m.
NED1 Entity disambiguation (via context triple) batch_69f43f15873881909e98e79283056573 completed May 1, 2026, 5:50 a.m.
Created at: April 8, 2026, 9:32 p.m.