Triple

T3267435
Position Surface form Disambiguated ID Type / Status
Subject BESIX E68559 entity
Predicate hasSubsidiary P254 FINISHED
Object BESIX Infra E68559 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: BESIX Infra | Statement: [BESIX, hasSubsidiary, BESIX Infra]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: BESIX Infra
Context triple: [BESIX, hasSubsidiary, BESIX Infra]
  • A. BESIX chosen
    BESIX is a major Belgian construction and engineering company known for delivering large-scale, high-profile projects worldwide.
  • B. Hochtief
    Hochtief is a major German-based global construction group known for large-scale infrastructure, engineering, and building projects worldwide.
  • C. Hollandse Beton Groep
    Hollandse Beton Groep was a major Dutch construction and civil engineering company known for its role in large-scale infrastructure and hydraulic engineering projects.
  • D. Tractebel
    Tractebel is an international engineering and consulting company specializing in energy, water, and infrastructure projects.
  • E. Kiewit Constructors
    Kiewit Constructors is a major North American construction and engineering contractor known for delivering large-scale infrastructure and transportation projects.
  • 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_69ad8590444081909e8107a8aeef3a23 completed March 8, 2026, 2:20 p.m.
NER Named-entity recognition batch_69adafce46dc8190a157e4f5012baed5 completed March 8, 2026, 5:20 p.m.
NED1 Entity disambiguation (via context triple) batch_69b28ef261ec819091c62620765e2cef completed March 12, 2026, 10:01 a.m.
Created at: March 8, 2026, 3:09 p.m.