Triple
T26283859
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Umar Gul |
E661076
|
entity |
| Predicate | bowlingTypeSpeciality |
P132605
|
FINISHED |
| Object | death overs specialist |
—
|
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: death overs specialist | Statement: [Umar Gul, bowlingTypeSpeciality, death overs specialist]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: bowlingTypeSpeciality Context triple: [Umar Gul, bowlingTypeSpeciality, death overs specialist]
-
A.
bowlingSpecialty
chosen
Indicates that one entity has a particular area of skill or expertise in the sport of bowling with respect to another entity or context.
-
B.
bowlingStrategy
Indicates the specific tactical approach or plan a bowler uses to deliver balls in order to challenge or dismiss a batter.
-
C.
bowlingStrength
Indicates the degree or effectiveness of one entity’s bowling performance or capability in relation to another.
-
D.
associatedWithBowlingStyleOfPerson
Indicates a relationship where something is linked to or characterized by the specific bowling style used by a person.
-
E.
bowlingSupportFor
Indicates that one entity provides assistance, resources, or encouragement to another entity specifically in the context of bowling activities or performance.
- 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_69ee812bbd448190be4d7478b057990a |
completed | April 26, 2026, 9:18 p.m. |
| NER | Named-entity recognition | batch_69f60e7593c881908faeda8a64f3e246 |
completed | May 2, 2026, 2:47 p.m. |
| PD | Predicate disambiguation | batch_69f5f7ff548c8190a23e98c5e66e0bc7 |
completed | May 2, 2026, 1:11 p.m. |
Created at: April 26, 2026, 10:02 p.m.