Triple

T11107105
Position Surface form Disambiguated ID Type / Status
Subject Nhat Tan Bridge E262658 entity
Predicate builder P3143 FINISHED
Object Taisei Corporation E386047 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: Taisei Corporation | Statement: [Nhat Tan Bridge, builder, Taisei Corporation]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Taisei Corporation
Context triple: [Nhat Tan Bridge, builder, Taisei Corporation]
  • A. Taisei Corporation chosen
    Taisei Corporation is a major Japanese construction and civil engineering company known for leading large-scale infrastructure and landmark building projects in Japan and abroad.
  • B. Takenaka Corporation
    Takenaka Corporation is a major Japanese architecture, engineering, and construction firm known for designing and building prominent structures domestically and internationally.
  • C. Obayashi Corporation
    Obayashi Corporation is a major Japanese construction and engineering company known for its involvement in large-scale infrastructure and building projects worldwide.
  • D. Komatsu Limited
    Komatsu Limited is a major Japanese multinational corporation that manufactures construction, mining, and military equipment.
  • E. Yoshimoto Kogyo
    Yoshimoto Kogyo is a major Japanese entertainment conglomerate best known for managing comedians and producing comedy shows, theater, television, and other media.
  • 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_69d6aa9a40d88190a373e2c7e48285db completed April 8, 2026, 7:20 p.m.
NER Named-entity recognition batch_69d79a6546d4819092187e9c12a30ed5 completed April 9, 2026, 12:24 p.m.
NED1 Entity disambiguation (via context triple) batch_69e42d7016908190bb7aadadacb5b50f completed April 19, 2026, 1:18 a.m.
Created at: April 8, 2026, 9:27 p.m.