Triple

T18658146
Position Surface form Disambiguated ID Type / Status
Subject Pandoh E456119 entity
Predicate nearbyCity P350 FINISHED
Object Mandi 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: Mandi | Statement: [Pandoh, nearbyCity, Mandi]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mandi
Context triple: [Pandoh, nearbyCity, Mandi]
  • A. Mandi chosen
    Mandi is a historic town and important commercial and cultural center located along the Beas River in the Indian state of Himachal Pradesh.
  • B. Mandi
    Mandi is a critically acclaimed 1983 Indian satirical film directed by Shyam Benegal, known for its ensemble cast and sharp social commentary on politics, morality, and the sex trade.
  • C. Mandi Kani
    Mandi Kani is the wife of renowned South African actor, director, and playwright John Kani.
  • D. Mundhwa
    Mundhwa is a rapidly developing residential and commercial suburb in eastern Pune, India, known for its mix of industrial estates, new housing projects, and proximity to major IT and lifestyle hubs.
  • E. Manjhand
    Manjhand is a town in Pakistan’s Sindh province, situated within the Jamshoro District along the Indus River region.
  • 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_69d8d38ea1e88190997e9b231190ba6f completed April 10, 2026, 10:40 a.m.
NER Named-entity recognition batch_69e55087ae8081909cb4c0ce6c809d55 completed April 19, 2026, 10 p.m.
Created at: April 10, 2026, 11:48 a.m.