Triple
T11510168
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Princely State of Swat |
E272888
|
entity |
| Predicate | capital |
P234
|
FINISHED |
| Object | Saidu Sharif |
E181671
|
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: Saidu Sharif | Statement: [Princely State of Swat, capital, Saidu Sharif]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Saidu Sharif Context triple: [Princely State of Swat, capital, Saidu Sharif]
-
A.
Saidu Sharif
chosen
Saidu Sharif is a town in Pakistan’s Swat Valley that serves as an administrative and cultural center for the region.
-
B.
Shamsuddin
Shamsuddin is an honorific title of Islamic origin commonly borne by rulers and notable figures, particularly in medieval Muslim dynasties such as the Habshi dynasty.
-
C.
Abdul Latif
Abdul Latif is the given name of Shah Abdul Latif Bhittai, the revered 18th-century Sindhi Sufi poet and saint.
-
D.
Najaf Ali Khan
Najaf Ali Khan was a prominent historical figure whose legacy is reflected in the naming of the Najafi dynasty.
-
E.
Haji Muhammad Mohsin
Haji Muhammad Mohsin was a prominent 18th–19th century Bengali philanthropist and social reformer renowned for his extensive charitable endowments in education and public welfare.
- 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_69d6aae2c3748190bed2ea50dfb160dc |
completed | April 8, 2026, 7:22 p.m. |
| NER | Named-entity recognition | batch_69d86db65eb081908613a1002c6a4fb4 |
completed | April 10, 2026, 3:25 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69e6852a23688190a3fe8e5508435661 |
completed | April 20, 2026, 7:57 p.m. |
Created at: April 8, 2026, 9:36 p.m.