Triple
T31673826
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 2000 Summer Olympics opening ceremony |
E808342
|
entity |
| Predicate | cauldronLighterOccupation |
P172627
|
FINISHED |
| Object | sprinter |
—
|
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: sprinter | Statement: [2000 Summer Olympics opening ceremony, cauldronLighterOccupation, sprinter]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: cauldronLighterOccupation Context triple: [2000 Summer Olympics opening ceremony, cauldronLighterOccupation, sprinter]
-
A.
cauldronLighter
Indicates that an entity performs the action of lighting or igniting a cauldron.
-
B.
torchLighterOccupation
Indicates that one entity’s occupation or job role is that of a torch lighter in relation to the other entity.
-
C.
primaryOccupationUnderWitch
Indicates that an entity’s main job or role is performed under the authority, control, or influence of a witch.
-
D.
cauldronDesigner
Indicates that one entity is the designer or creator of a particular cauldron associated with another entity.
-
E.
cauldronLocation
Indicates the spatial location or placement of a cauldron relative to some reference (such as a place, object, or region).
- 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_69f348dcf5d48190ac25b1365ae717a8 |
completed | April 30, 2026, 12:19 p.m. |
| NER | Named-entity recognition | batch_69f6ac1ed23c8190ace57ffc9d8a3dc6 |
completed | May 3, 2026, 1:59 a.m. |
| PD | Predicate disambiguation | batch_69f6aa1e84b88190b025f6ca40f17a8a |
completed | May 3, 2026, 1:51 a.m. |
| PDg | Predicate description generation | batch_69f6aba8fba48190bc1a17117244cae1 |
completed | May 3, 2026, 1:58 a.m. |
Created at: April 30, 2026, 11:02 p.m.