Triple

T7346452
Position Surface form Disambiguated ID Type / Status
Subject GrabFood E169392 entity
Predicate integratedIn P15157 FINISHED
Object Grab super app 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 super app | Statement: [GrabFood, integratedIn, Grab super app]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Grab super app
Context triple: [GrabFood, integratedIn, Grab super app]
  • A. Google Now Launcher
    Google Now Launcher was Google’s former Android home screen app that integrated Google Now cards and voice search directly into the launcher experience.
  • B. Mobile Launcher 2
    Mobile Launcher 2 was one of NASA’s Saturn V launch platforms at Kennedy Space Center, supporting Apollo-era missions by providing the structure and services needed to prepare and launch the rockets.
  • C. Expo Go
    Expo Go is a mobile app that lets developers instantly run and preview React Native projects on their devices without building native binaries.
  • D. Android Instant Apps
    Android Instant Apps is a Google Play feature that lets users run parts of Android apps instantly without installation, enabling quick, lightweight access to app experiences from links.
  • E. Grab chosen
    Grab is a Southeast Asian super-app company best known for its ride-hailing, food delivery, and digital payments services.
  • 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_69c68a5878888190968ce4d04db8d69f completed March 27, 2026, 1:47 p.m.
NER Named-entity recognition batch_69c6f0f0329c8190a0182e3bf62604e5 completed March 27, 2026, 9:04 p.m.
NED1 Entity disambiguation (via context triple) batch_69c7fa916ac881909acee8184b71dc85 completed March 28, 2026, 3:58 p.m.
Created at: March 27, 2026, 3:05 p.m.