Triple
T31836217
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tang Prize Foundation |
E812680
|
entity |
| Predicate | operatesAwardProgram |
P56516
|
FINISHED |
| Object | Tang Prize laureate selection |
—
|
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: Tang Prize laureate selection | Statement: [Tang Prize Foundation, operatesAwardProgram, Tang Prize laureate selection]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: operatesAwardProgram Context triple: [Tang Prize Foundation, operatesAwardProgram, Tang Prize laureate selection]
-
A.
hasAwardProgram
chosen
Indicates that an entity maintains or offers a formal award or recognition program.
-
B.
rewardProgramOperator
Indicates that one entity operates or manages a reward or loyalty program associated with another entity.
-
C.
mostAwardsProgram
Indicates that a program holds the highest number of awards compared to all other programs in the relevant set.
-
D.
offersGrantsProgram
Indicates that an entity provides or makes available a grants program to others.
-
E.
loyaltyProgramAccess
Indicates that an entity is granted rights or eligibility to participate in a specific loyalty or rewards program.
- 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_69f348ea7ffc8190a2ab43d80277cf59 |
completed | April 30, 2026, 12:19 p.m. |
| NER | Named-entity recognition | batch_69ffcb5536d88190bfc2e00b854cacfb |
completed | May 10, 2026, 12:03 a.m. |
| PD | Predicate disambiguation | batch_69ffc900c2a081909dea04aa60566923 |
completed | May 9, 2026, 11:53 p.m. |
Created at: April 30, 2026, 11:48 p.m.