Triple
T3788209
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bing Dwen Dwen |
E85579
|
entity |
| Predicate | officialForEvent |
P29298
|
FINISHED |
| Object | 2022 Beijing Winter Olympics |
—
|
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: 2022 Beijing Winter Olympics | Statement: [Bing Dwen Dwen, officialForEvent, 2022 Beijing Winter Olympics]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: officialForEvent Context triple: [Bing Dwen Dwen, officialForEvent, 2022 Beijing Winter Olympics]
-
A.
organisedFor
Indicates that something has been arranged, structured, or coordinated specifically to serve, support, or benefit a particular entity or purpose.
-
B.
madeForEvent
chosen
Indicates that something was created, produced, or designed specifically for use in a particular event.
-
C.
officialIn
Indicates that an entity holds an official position, role, or office within a specified organization, institution, or jurisdiction.
-
D.
officialFrom
Indicates that a person holds or held an official position representing or originating from a specified place, organization, or jurisdiction.
-
E.
organisedEvent
Indicates that an entity planned, coordinated, and carried out an event.
- 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_69aed937fa8881908208ef3801060826 |
completed | March 9, 2026, 2:29 p.m. |
| NER | Named-entity recognition | batch_69aee634c6ac819099653c660c286746 |
completed | March 9, 2026, 3:24 p.m. |
| PD | Predicate disambiguation | batch_69aee3d4bc3c81909bd56e33d43fa8e4 |
completed | March 9, 2026, 3:14 p.m. |
Created at: March 9, 2026, 3:13 p.m.