Triple

T9743407
Position Surface form Disambiguated ID Type / Status
Subject Tamil Nadu Secretariat E236245 entity
Predicate city P40 FINISHED
Object Chennai E12324 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: Chennai | Statement: [Tamil Nadu Secretariat, city, Chennai]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Chennai
Context triple: [Tamil Nadu Secretariat, city, Chennai]
  • A. Chennai chosen
    Chennai is a major coastal metropolis in southern India, serving as the capital of Tamil Nadu and a key cultural, economic, and automotive hub.
  • B. Tiruchirappalli
    Tiruchirappalli is a major city in the Indian state of Tamil Nadu, known for its historic temples, educational institutions, and strategic location along the Kaveri River.
  • C. Madras
    Madras is a small city in central Oregon known as an agricultural hub and gateway to outdoor recreation in the surrounding high desert region.
  • D. Madras
    Madras is an unincorporated community located in Coweta County in the U.S. state of Georgia.
  • E. Coimbatore
    Coimbatore is a major industrial and educational city in the Indian state of Tamil Nadu, known especially for its textile, engineering, and manufacturing industries.
  • 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_69ca84d3e24481908a476e2231123cf9 completed March 30, 2026, 2:12 p.m.
NER Named-entity recognition batch_69cd9f2e5bb081908047e3bf5fe3991c completed April 1, 2026, 10:41 p.m.
NED1 Entity disambiguation (via context triple) batch_69d1c40b0db081908b956484e3ff44c0 completed April 5, 2026, 2:08 a.m.
Created at: March 30, 2026, 8:23 p.m.