Triple
T19989809
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Shahzadi Zinat-un-Nissa Begum |
E494030
|
entity |
| Predicate | title |
P38
|
FINISHED |
| Object | Shahzadi |
—
|
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: Shahzadi | Statement: [Shahzadi Zinat-un-Nissa Begum, title, Shahzadi]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Shahzadi Context triple: [Shahzadi Zinat-un-Nissa Begum, title, Shahzadi]
-
A.
Shehera
Shehera is a town located in the Panchmahal district of the Indian state of Gujarat.
-
B.
Princess Azadeh Shafiq
Princess Azadeh Shafiq was a member of Iran’s Pahlavi royal family and the daughter of Princess Ashraf Pahlavi, known for her life in exile following the Iranian Revolution.
-
C.
Shah Khanum
Shah Khanum was the grandmother of Siraj ud-Daulah, the last independent Nawab of Bengal in the mid-18th century.
-
D.
Shahzada
Shahzada is a royal title used in Persianate and South Asian cultures to denote a prince or son of a monarch.
-
E.
Shahzadi Khanam
chosen
Shahzadi Khanam was a Mughal-era noblewoman best known as the daughter of the Bengal Nawab Alivardi Khan.
- 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_69da626a67648190af9653832a3aeced |
completed | April 11, 2026, 3:02 p.m. |
| NER | Named-entity recognition | batch_69e65fdecf108190a5b215fd25bc4dda |
completed | April 20, 2026, 5:18 p.m. |
Created at: April 11, 2026, 3:30 p.m.