Triple

T23152935
Position Surface form Disambiguated ID Type / Status
Subject The Tracey Fragments E578366 entity
Predicate productionCompany P490 FINISHED
Object Sodec NE NERFINISHED

How this triple was built (3 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: Sodec | Statement: [The Tracey Fragments, productionCompany, Sodec]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sodec
Context triple: [The Tracey Fragments, productionCompany, Sodec]
  • A. SODECO
    SODECO (Sakhalin Oil and Gas Development Co., Ltd.) is a Japanese consortium of energy and trading companies that invests in and develops overseas oil and gas projects, notably in Russia’s Sakhalin region.
  • B. Sogecine
    Sogecine is a Spanish film production company known for backing acclaimed auteur-driven cinema, including works by director Alejandro Amenábar.
  • C. Tractebel Energia
    Tractebel Energia is a Brazilian electric power generation company known for operating large hydroelectric facilities and other energy assets across the country.
  • D. Tractebel
    Tractebel is an international engineering and consulting company specializing in energy, water, and infrastructure projects.
  • E. Cegelec
    Cegelec is an international engineering and technology services company specializing in electrical, automation, and information systems for infrastructure and industry.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Sodec
Target entity description: Sodec is a Canadian film and television funding agency that supports the development and production of Quebec’s audiovisual works.
  • A. SODECO
    SODECO (Sakhalin Oil and Gas Development Co., Ltd.) is a Japanese consortium of energy and trading companies that invests in and develops overseas oil and gas projects, notably in Russia’s Sakhalin region.
  • B. Sogecine
    Sogecine is a Spanish film production company known for backing acclaimed auteur-driven cinema, including works by director Alejandro Amenábar.
  • C. Tractebel Energia
    Tractebel Energia is a Brazilian electric power generation company known for operating large hydroelectric facilities and other energy assets across the country.
  • D. Tractebel
    Tractebel is an international engineering and consulting company specializing in energy, water, and infrastructure projects.
  • E. Cegelec
    Cegelec is an international engineering and technology services company specializing in electrical, automation, and information systems for infrastructure and industry.
  • F. None of above. chosen

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_69e245fb8de081908f0eba7b5fd75bc4 completed April 17, 2026, 2:38 p.m.
NER Named-entity recognition batch_69f18efaa1fc81908fb1987dbf732f46 completed April 29, 2026, 4:54 a.m.
Created at: April 17, 2026, 4:01 p.m.