Triple

T4959019
Position Surface form Disambiguated ID Type / Status
Subject Porbandar district E111357 entity
Predicate hasPort P35 FINISHED
Object Porbandar port E103049 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: Porbandar port | Statement: [Porbandar district, hasPort, Porbandar port]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Porbandar port
Context triple: [Porbandar district, hasPort, Porbandar port]
  • A. Porbandar chosen
    Porbandar is a coastal city in the Indian state of Gujarat, best known as the birthplace of Mahatma Gandhi and an important historical and religious center.
  • B. Pipavav Port
    Pipavav Port is a major private deep-water port on India’s western coast, serving as an important hub for container, bulk, and liquid cargo trade.
  • C. 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.
  • D. Karwar Port
    Karwar Port is a coastal seaport in Karnataka, India, serving as a regional maritime hub for trade, fishing, and naval operations along the Arabian Sea.
  • E. Mundra Port
    Mundra Port is India’s largest commercial port and a major deep-draft, all-weather cargo hub located on the Arabian Sea coast in the state of Gujarat.
  • 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_69bd4418390c8190b7e9766a2512ce55 completed March 20, 2026, 12:56 p.m.
NER Named-entity recognition batch_69bd71d957cc8190b82fdd1ca61924bf completed March 20, 2026, 4:12 p.m.
NED1 Entity disambiguation (via context triple) batch_69be9244fb008190baee4ade5b00691f completed March 21, 2026, 12:42 p.m.
Created at: March 20, 2026, 1:32 p.m.