Triple
T16527545
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Shabana Azmi |
E401479
|
entity |
| Predicate | notableWork |
P4
|
FINISHED |
| Object | Khandhar |
E496018
|
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: Khandhar | Statement: [Shabana Azmi, notableWork, Khandhar]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Khandhar Context triple: [Shabana Azmi, notableWork, Khandhar]
-
A.
Khandhar
chosen
Khandhar is a 1984 Indian art-house film directed by Mrinal Sen, acclaimed for its poignant portrayal of loneliness and decay in a rural setting.
-
B.
Kandhkot
Kandhkot is a town in Pakistan’s Sindh province that serves as a key urban and commercial center in the Kashmore District.
-
C.
Khoshbagh
Khoshbagh is a historic garden-cemetery complex in Murshidabad, West Bengal, known as the burial place of several Nawabs of Bengal.
-
D.
Sur Khahori
Sur Khahori is a poetic chapter of the classic Sindhi Sufi anthology Shah Jo Risalo, expressing themes of devotion and spiritual longing.
-
E.
Saida Khera
Saida Khera is a village in Punjab, India, known in folklore as a setting linked to the legendary love story of Heer Ranjha.
- 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_69d883838abc8190bc79cb2d41733ce2 |
completed | April 10, 2026, 4:58 a.m. |
| NER | Named-entity recognition | batch_69e32ed4b8a08190b5f179fc583001a6 |
completed | April 18, 2026, 7:12 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a00608efd0c81908e64419bd74eb285 |
completed | May 10, 2026, 10:40 a.m. |
Created at: April 10, 2026, 5:14 a.m.