Triple

T23108239
Position Surface form Disambiguated ID Type / Status
Subject Narmadapuram Division E576235 entity
Predicate containsSettlement P847 FINISHED
Object Harda 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: Harda | Statement: [Narmadapuram Division, containsSettlement, Harda]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Harda
Context triple: [Narmadapuram Division, containsSettlement, Harda]
  • A. Harda chosen
    Harda is a town and administrative district headquarters in the central Indian state of Madhya Pradesh, known for its agricultural economy and railway connectivity.
  • B. Vidisha
    Vidisha is a historic city in the central Indian state of Madhya Pradesh, known for its ancient Buddhist and Hindu heritage and archaeological sites.
  • C. Anupgarh
    Anupgarh is a town in the Ganganagar district of Rajasthan, India, known for its agricultural surroundings and proximity to the India–Pakistan border.
  • D. Sarangpur
    Sarangpur is a prominent town and commercial center in the Malwa region of Madhya Pradesh, India, known for its historical and religious significance.
  • E. Sarangpur
    Sarangpur is a town in Gujarat, India, known as an important religious center for the Swaminarayan Sampradaya and a site of major Hindu temples and pilgrimage.
  • 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_69e245f4af548190898d434a64a1e774 completed April 17, 2026, 2:38 p.m.
NER Named-entity recognition batch_69f18e0c7b9c8190b1160485eae87c9b completed April 29, 2026, 4:50 a.m.
Created at: April 17, 2026, 3:58 p.m.