Triple
T13126302
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ghilji |
E311851
|
entity |
| Predicate | hasTribe |
P32607
|
FINISHED |
| Object |
Taraki
Taraki is a Pashtun sub-tribe within the larger Ghilji tribal confederation of Afghanistan.
|
E1022402
|
NE FINISHED |
How this triple was built (4 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: Taraki | Statement: [Ghilji, hasTribe, Taraki]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Taraki Context triple: [Ghilji, hasTribe, Taraki]
-
A.
Tagau Pashayi
Tagau Pashayi is a specific variety of the Pashayi languages spoken by Pashayi communities in eastern Afghanistan.
-
B.
Kuz Kunar Pashayi
Kuz Kunar Pashayi is a regional variety of the Pashayi language spoken by communities in and around the Kuz Kunar area of eastern Afghanistan.
-
C.
Sachal
Sachal is the honorific name of Sachal Sarmast, an 18th–19th century Sindhi Sufi poet and mystic renowned for his multilingual poetry and message of spiritual unity.
-
D.
Taha
Taha is a family name most notably associated with Mahmoud Mohammed Taha, a prominent Sudanese Islamic reformer and thinker.
-
E.
Miranshah
Miranshah is the main administrative and commercial town of North Waziristan in Pakistan’s Khyber Pakhtunkhwa province, near the border with Afghanistan.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Taraki Triple: [Ghilji, hasTribe, Taraki]
Generated description
Taraki is a Pashtun sub-tribe within the larger Ghilji tribal confederation of Afghanistan.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Taraki Target entity description: Taraki is a Pashtun sub-tribe within the larger Ghilji tribal confederation of Afghanistan.
-
A.
Tagau Pashayi
Tagau Pashayi is a specific variety of the Pashayi languages spoken by Pashayi communities in eastern Afghanistan.
-
B.
Kuz Kunar Pashayi
Kuz Kunar Pashayi is a regional variety of the Pashayi language spoken by communities in and around the Kuz Kunar area of eastern Afghanistan.
-
C.
Sachal
Sachal is the honorific name of Sachal Sarmast, an 18th–19th century Sindhi Sufi poet and mystic renowned for his multilingual poetry and message of spiritual unity.
-
D.
Taha
Taha is a family name most notably associated with Mahmoud Mohammed Taha, a prominent Sudanese Islamic reformer and thinker.
-
E.
Miranshah
Miranshah is the main administrative and commercial town of North Waziristan in Pakistan’s Khyber Pakhtunkhwa province, near the border with Afghanistan.
- F. None of above. chosen
Provenance (5 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_69d806a9fe888190b081e2d9ea665d6c |
completed | April 9, 2026, 8:06 p.m. |
| NER | Named-entity recognition | batch_69d9819aac388190b59bf43cc6a49d0c |
completed | April 10, 2026, 11:02 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f6e28bdd6881909d01e550e99267e1 |
completed | May 3, 2026, 5:52 a.m. |
| NEDg | Description generation | batch_69f6e383dd8c8190872304c99b753152 |
completed | May 3, 2026, 5:56 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69f6e47b052c8190a6f6ca5a6bd210f5 |
completed | May 3, 2026, 6 a.m. |
Created at: April 9, 2026, 9:07 p.m.