Triple
T15004482
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | administration of Akbar |
E377673
|
entity |
| Predicate | office |
P3103
|
FINISHED |
| Object | Mir Bakshi |
E334690
|
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: Mir Bakshi | Statement: [administration of Akbar, office, Mir Bakshi]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mir Bakshi Context triple: [administration of Akbar, office, Mir Bakshi]
-
A.
Mir Bakshi
chosen
Mir Bakshi was a high-ranking Mughal imperial official responsible for military administration and the management of army personnel and payments.
-
B.
Mukul Sharma
Mukul Sharma was an Indian writer, journalist, and science fiction author known for his popular science columns and for inspiring several acclaimed film adaptations.
-
C.
Ashok Saraf
Ashok Saraf is a veteran Indian actor and comedian best known for his prolific work in Marathi films and theatre, as well as memorable roles in Hindi cinema and television.
-
D.
Brij Mohan
Brij Mohan is the given name of B. M. Kaul, an individual identifiable by the initials B.M. Kaul.
-
E.
Jitendra Malik
Jitendra Malik is a prominent computer scientist known for his influential work in computer vision and machine learning, and for mentoring leading researchers in the field.
- 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_69d85cd3a3c881908c71fc424d459c17 |
completed | April 10, 2026, 2:13 a.m. |
| NER | Named-entity recognition | batch_69ded7322b5c81909089cbbf816e1436 |
completed | April 15, 2026, 12:09 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fe96a04eec8190b347bf3637aba0bc |
completed | May 9, 2026, 2:06 a.m. |
Created at: April 10, 2026, 2:54 a.m.