Triple

T14051765
Position Surface form Disambiguated ID Type / Status
Subject Cross Island E338107 entity
Predicate locatedIn P40 FINISHED
Object Mumbai Harbour E67210 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: Mumbai Harbour | Statement: [Cross Island, locatedIn, Mumbai Harbour]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mumbai Harbour
Context triple: [Cross Island, locatedIn, Mumbai Harbour]
  • A. Mumbai Harbour chosen
    Mumbai Harbour is a natural deep-water harbor on the eastern shore of Mumbai, India, serving as a major maritime gateway and commercial port on the Arabian Sea.
  • B. Mumbai waterfront
    The Mumbai waterfront is a prominent coastal stretch of the city featuring historic landmarks, promenades, and harbors along the Arabian Sea.
  • C. Mazagaon
    Mazagaon is one of the original seven islands that historically merged to form the modern city of Mumbai, India.
  • D. Indoji Port
    Indoji Port is a harbor facility located on Iki Island in Japan, serving as one of the island’s key maritime access points.
  • E. Mumbai Island
    Mumbai Island is a historic island region that forms the core part of the modern city of Mumbai on India’s western coast.
  • 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_69d81c664e48819088cbd8f433aeffe5 completed April 9, 2026, 9:38 p.m.
NER Named-entity recognition batch_69de3c8a518081908ad030ba48b7b946 completed April 14, 2026, 1:09 p.m.
NED1 Entity disambiguation (via context triple) batch_69fcb65e63b48190bd5bd4a36cd15396 completed May 7, 2026, 3:57 p.m.
Created at: April 9, 2026, 10:20 p.m.