Triple

T23090988
Position Surface form Disambiguated ID Type / Status
Subject Firestone Building Products E575747 entity
Predicate parentCompany P254 FINISHED
Object Holcim 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: Holcim | Statement: [Firestone Building Products, parentCompany, Holcim]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Holcim
Context triple: [Firestone Building Products, parentCompany, Holcim]
  • A. Holcim chosen
    Holcim is a global leader in innovative and sustainable building materials and construction solutions.
  • B. Cemex
    Cemex is a global building materials company headquartered in Mexico, best known as one of the world’s largest producers of cement, ready-mix concrete, and aggregates.
  • C. Eagle Cement
    Eagle Cement is the former name of Dolphins F.C., a Nigerian professional football club.
  • D. Saint-Gobain
    Saint-Gobain is a major French multinational corporation specializing in the production and distribution of construction materials and high-performance solutions for buildings and industry.
  • E. Limak Cement
    Limak Cement is a Turkish cement and building materials company operating as a key subsidiary of the diversified Limak Group.
  • 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_69e245bf3e3c819086d3448720efc01b completed April 17, 2026, 2:37 p.m.
NER Named-entity recognition batch_69f18da99bec81908ecadf8dab10d1b7 completed April 29, 2026, 4:48 a.m.
Created at: April 17, 2026, 3:57 p.m.