Triple
T37836657
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | ლევან კობიაშვილი |
E943355
|
entity |
| Predicate | პოზიცია_ფეხბურთში |
P154438
|
FINISHED |
| Object | მარცხენა ნახევარმცველი |
—
|
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: მარცხენა ნახევარმცველი | Statement: [ლევან კობიაშვილი, პოზიცია_ფეხბურთში, მარცხენა ნახევარმცველი]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: პოზიცია_ფეხბურთში Context triple: [ლევან კობიაშვილი, პოზიცია_ფეხბურთში, მარცხენა ნახევარმცველი]
-
A.
penaltyTakerPosition
Indicates the playing position or role of the player who takes a penalty.
-
B.
typicalPlayingPosition
chosen
Indicates the usual role or position an entity regularly occupies when participating in a game, sport, or similar activity.
-
C.
typeOfFootball
Indicates the specific code or variant of football that characterizes or classifies a given football-related entity.
-
D.
positionInCourt
Indicates the specific role or standing an entity holds within a court setting or judicial proceeding.
-
E.
fieldOfPlay
Indicates the spatial area or surface where an activity, event, or interaction takes place.
- F. None of above.
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_69f76eeb0f7081908d6d3adbc469889c |
completed | May 3, 2026, 3:51 p.m. |
| NER | Named-entity recognition | batch_69fbbae559a8819086ef839973f8d9b2 |
completed | May 6, 2026, 10:04 p.m. |
| PD | Predicate disambiguation | batch_69fbb1440fa08190abf25ba684f75b6e |
completed | May 6, 2026, 9:23 p.m. |
Created at: May 3, 2026, 4:19 p.m.