Triple
T8420670
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hindko |
E198840
|
entity |
| Predicate | ethnicityAssociated |
P1969
|
FINISHED |
| Object | Hindkowan |
E272889
|
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: Hindkowan | Statement: [Hindko, ethnicityAssociated, Hindkowan]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Hindkowan Context triple: [Hindko, ethnicityAssociated, Hindkowan]
-
A.
Hindkowans
chosen
Hindkowans are an Indo-Aryan ethnic group primarily associated with the Hindko language and concentrated in northern and central regions of Pakistan, especially in and around the Hazara area.
-
B.
Umarkot
Umarkot is a historic town in the Sindh province of Pakistan, traditionally known as the birthplace of the Mughal emperor Akbar.
-
C.
Chanhudaro
Chanhudaro is an archaeological site in present-day Pakistan known as a smaller but significant urban center of the Indus Valley Civilization, notable for its craft production and bead-making.
-
D.
Pakhoras
Pakhoras is the ancient name of Faras, a significant archaeological and historical site in Nubia known for its medieval Christian cathedral and wall paintings.
-
E.
Kalasha
Kalasha is an endangered Indo-Aryan language spoken by the Kalash people in the remote valleys of northern Pakistan.
- 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_69ca8312d63c8190bf133b676b44a385 |
completed | March 30, 2026, 2:05 p.m. |
| NER | Named-entity recognition | batch_69cb84ca7b348190abab25e79b05407f |
completed | March 31, 2026, 8:24 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ce1d469a148190a6f018f758cba5eb |
completed | April 2, 2026, 7:39 a.m. |
Created at: March 30, 2026, 6:06 p.m.