Triple

T18451164
Position Surface form Disambiguated ID Type / Status
Subject Delhi Daredevils E450784 entity
Predicate owner P347 FINISHED
Object GMR Group NE NERFINISHED

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: GMR Group | Statement: [Delhi Daredevils, owner, GMR Group]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: GMR Group
Context triple: [Delhi Daredevils, owner, GMR Group]
  • A. GMR Group chosen
    GMR Group is a leading Indian infrastructure conglomerate with major interests in airports, energy, transportation, and urban infrastructure development.
  • B. GMR Airports
    GMR Airports is an Indian airport development and operations company that manages and operates multiple airports in India and abroad as part of the GMR Group’s infrastructure portfolio.
  • C. Ferrovial
    Ferrovial is a multinational Spanish infrastructure and construction company known for developing and operating major transport projects such as highways and airports worldwide.
  • D. GPT Group
    GPT Group is an Australian property investment and management company specializing in owning and operating retail shopping centres and commercial real estate.
  • E. Egis Group
    Egis Group is a global engineering and infrastructure consulting firm that manages and operates transportation facilities such as airports, roads, and urban transit systems.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69d8d38345688190b565eac2e4cd7935 completed April 10, 2026, 10:40 a.m.
NER Named-entity recognition batch_69e52648476c8190a5d8c3297d836f62 completed April 19, 2026, 7 p.m.
Created at: April 10, 2026, 11:31 a.m.