Triple

T5878246
Position Surface form Disambiguated ID Type / Status
Subject Post Tower E130678 entity
Predicate mainContractor P7138 FINISHED
Object Hochtief E261848 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: Hochtief | Statement: [Post Tower, mainContractor, Hochtief]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Hochtief
Context triple: [Post Tower, mainContractor, Hochtief]
  • A. Hochtief chosen
    Hochtief is a major German-based global construction group known for large-scale infrastructure, engineering, and building projects worldwide.
  • B. BESIX
    BESIX is a major Belgian construction and engineering company known for delivering large-scale, high-profile projects worldwide.
  • C. Skanska AB
    Skanska AB is a multinational Swedish construction and project development company known for large-scale infrastructure, commercial, and residential projects worldwide.
  • D. Eiffage
    Eiffage is a major French construction and civil engineering company known for delivering large-scale infrastructure projects such as the Millau Viaduct.
  • E. ThyssenKrupp AG
    ThyssenKrupp AG is a major German multinational conglomerate specializing in industrial engineering and steel production, with significant operations in areas such as elevators, automotive components, and plant technology.
  • 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_69c0085523688190bfd487479ce819e6 completed March 22, 2026, 3:18 p.m.
NER Named-entity recognition batch_69c036327efc8190858e9364cd5d317b completed March 22, 2026, 6:34 p.m.
NED1 Entity disambiguation (via context triple) batch_69c0b12861c081909f95f1ef6a1f457c completed March 23, 2026, 3:19 a.m.
Created at: March 22, 2026, 3:57 p.m.