Triple
T37157766
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Afghan buzkashi |
E920556
|
entity |
| Predicate | chapandazDefinition |
P187216
|
FINISHED |
| Object | highly skilled buzkashi rider |
—
|
LITERAL 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: highly skilled buzkashi rider | Statement: [Afghan buzkashi, chapandazDefinition, highly skilled buzkashi rider]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: chapandazDefinition Context triple: [Afghan buzkashi, chapandazDefinition, highly skilled buzkashi rider]
-
A.
kāṇḍa
Indicates a part–whole relationship where something is a section, chapter, or subdivision of a larger structured whole.
-
B.
ছন্দ
Indicates a relationship where something follows or embodies a rhythmic, metrical, or patterned flow, as in verse, music, or coordinated movement.
-
C.
pakad
Indicates the act of catching, holding, or seizing someone or something, typically by grasping or capturing it.
-
D.
isUpapandava
Indicates that one entity is an Upapandava, i.e., a son or secondary descendant of the Pandavas, in relation to a specified context or lineage.
-
E.
חל
Indicates that a state, condition, rule, or effect applies to, is in force for, or takes effect upon a given entity or situation.
- F. None of above. chosen
Provenance (4 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_69f76ea0429081908c711b55599eac3c |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_69fb344c60f8819090f2e21e1e61d621 |
completed | May 6, 2026, 12:30 p.m. |
| PD | Predicate disambiguation | batch_69fb2f642db08190b562725502c74ea6 |
completed | May 6, 2026, 12:09 p.m. |
| PDg | Predicate description generation | batch_69fb344ba5408190a6fe8face293d88b |
completed | May 6, 2026, 12:30 p.m. |
Created at: May 3, 2026, 4:15 p.m.