Triple

T633951
Position Surface form Disambiguated ID Type / Status
Subject SoftBank Vision Fund E15980 entity
Predicate investsIn P17330 FINISHED
Object Grab E30981 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: Grab | Statement: [SoftBank Vision Fund, investsIn, Grab]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Grab
Context triple: [SoftBank Vision Fund, investsIn, Grab]
  • A. Grab chosen
    Grab is a Southeast Asian super-app company best known for its ride-hailing, food delivery, and digital payments services.
  • B. GAB
    GAB is the three-letter ISO 3166-1 alpha-3 country code assigned to Gabon.
  • C. Hook
    Hook is a village in Hampshire, England, known as a commuter settlement with good transport links to nearby towns and London.
  • D. Kick
    Kick was the affectionate nickname of Kathleen Kennedy Cavendish, the socially prominent and charismatic sister of U.S. President John F. Kennedy.
  • E. GN
    GN is a fast, meta-build system tool used primarily by the Chromium project to generate build files for Ninja.
  • 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_69a4935c131c8190a5378c6bf101e8cc completed March 1, 2026, 7:28 p.m.
NER Named-entity recognition batch_69a4a515ceb081908c064b2082047c0f completed March 1, 2026, 8:44 p.m.
NED1 Entity disambiguation (via context triple) batch_69a56ef052308190bfaed448c3737ef6 completed March 2, 2026, 11:05 a.m.
Created at: March 1, 2026, 7:35 p.m.