Triple
T13417914
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hotak tribe |
E313261
|
entity |
| Predicate | alternativeName |
P39
|
FINISHED |
| Object | Hotaki |
E311855
|
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: Hotaki | Statement: [Hotak tribe, alternativeName, Hotaki]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Hotaki Context triple: [Hotak tribe, alternativeName, Hotaki]
-
A.
Hotaki
chosen
Hotaki refers to a member or native of the Hotak dynasty, an Afghan Pashtun ruling family that briefly controlled parts of Persia and Afghanistan in the early 18th century.
-
B.
Tokhi
Tokhi is a prominent Pashtun tribe that forms part of the larger Ghilji tribal confederation in Afghanistan.
-
C.
Kalhori
Kalhori is a major dialect of Southern Kurdish spoken primarily in western Iran, particularly in parts of Kermanshah and Ilam provinces.
-
D.
Khotta
Khotta is an alternate name for the Khortha language, an Indo-Aryan language spoken primarily in the Indian state of Jharkhand.
-
E.
Shahbad Markanda
Shahbad Markanda is a town in the Kurukshetra district of Haryana, India, known for its agricultural trade and historical significance in the region.
- 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_69d806ad0c44819088833ae1ec9e9690 |
completed | April 9, 2026, 8:06 p.m. |
| NER | Named-entity recognition | batch_69dbaeb8416c8190a00dde0917c26f51 |
completed | April 12, 2026, 2:39 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f73082a2548190aefc0f202b84165c |
completed | May 3, 2026, 11:24 a.m. |
Created at: April 9, 2026, 9:39 p.m.