Triple
T3569419
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mahmud Shah Durrani |
E75530
|
entity |
| Predicate | title |
P38
|
FINISHED |
| Object | Shah |
E365310
|
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: Shah | Statement: [Mahmud Shah Durrani, title, Shah]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Shah Context triple: [Mahmud Shah Durrani, title, Shah]
-
A.
Shah
chosen
Shah is a royal title historically used for monarchs and rulers in Persia (Iran) and other regions of the Islamic world.
-
B.
Rahbar
Rahbar is the title commonly used for the Supreme Leader of Iran, the country's highest political and religious authority.
-
C.
Khosrowshahi
Khosrowshahi is a Persian surname most prominently associated with Dara Khosrowshahi, the Iranian-American business executive and CEO of Uber.
-
D.
Khusrav Mirza
Khusrav Mirza was a Mughal prince of the early 17th century, known for rebelling against his father Emperor Jahangir and becoming a focal point in the empire’s succession struggles.
-
E.
Mirza
Mirza is a historical noble title of Persian and Central Asian origin, commonly borne by princes and high-ranking members of royal and aristocratic families.
- 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_69ad85d512708190829c8b2d3a2ccfb8 |
completed | March 8, 2026, 2:21 p.m. |
| NER | Named-entity recognition | batch_69adc0c1ecb081909051bcc1f38eea31 |
completed | March 8, 2026, 6:32 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b402ebfd548190a155fb1e65aefa8d |
completed | March 13, 2026, 12:28 p.m. |
Created at: March 8, 2026, 3:21 p.m.