Triple

T17128381
Position Surface form Disambiguated ID Type / Status
Subject Puri district E415657 entity
Predicate contains P35 FINISHED
Object Puri E476598 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: Puri | Statement: [Puri district, contains, Puri]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Puri
Context triple: [Puri district, contains, Puri]
  • A. Puri chosen
    Puri is a coastal city in the Indian state of Odisha, renowned as a major Hindu pilgrimage site and home to the famous Jagannath Temple.
  • B. Tamralipti
    Tamralipti was an ancient and prominent port city on the eastern coast of the Indian subcontinent that served as a key maritime hub for trade and cultural exchange between India and Southeast Asia.
  • C. Vikrampura
    Vikrampura was an important historical city that served as a principal royal center of the medieval Indian Pala dynasty in eastern India.
  • D. Mandapam
    Mandapam is a coastal town in Tamil Nadu, India, known as a gateway to Rameswaram and for its fishing and marine activities.
  • E. Lakdikapul
    Lakdikapul is a prominent commercial and transit locality in central Hyderabad, known for its busy roads, hotels, and connectivity to major city hubs.
  • 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_69d886d15af4819092f92f8a129763e6 completed April 10, 2026, 5:12 a.m.
NER Named-entity recognition batch_69e3f0285a408190ae5e4c4679c07fbf completed April 18, 2026, 8:57 p.m.
NED1 Entity disambiguation (via context triple) batch_6a0170e153808190b2a253f64da87737 completed May 11, 2026, 6:02 a.m.
Created at: April 10, 2026, 5:36 a.m.