Triple
T1568699
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 2014 Winter Olympics |
E33489
|
entity |
| Predicate | torchRelayNotableFeature |
P29545
|
FINISHED |
| Object | spacewalk with Olympic torch on ISS |
—
|
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: spacewalk with Olympic torch on ISS | Statement: [2014 Winter Olympics, torchRelayNotableFeature, spacewalk with Olympic torch on ISS]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: torchRelayNotableFeature Context triple: [2014 Winter Olympics, torchRelayNotableFeature, spacewalk with Olympic torch on ISS]
-
A.
torchRelay
Indicates a sequential passing of a ceremonial torch from one participant or location to another as part of a relay event.
-
B.
torchRelayEndDate
Indicates the date on which a torch relay event or sequence officially concludes.
-
C.
torchLighter
Indicates that one entity lights, ignites, or operates a torch for another entity or in relation to another entity.
-
D.
neuralEngineType
Indicates the specific kind or category of neural processing engine associated with or used by an entity.
-
E.
torchDesign
Indicates that an entity is responsible for creating or specifying the design of a torch.
- 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_69a885f11b048190935025a035302715 |
completed | March 4, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69a90fccd4b48190a44012888a00af7f |
completed | March 5, 2026, 5:08 a.m. |
| PD | Predicate disambiguation | batch_69a907b872f0819096b3df6ad502c63e |
completed | March 5, 2026, 4:34 a.m. |
| PDg | Predicate description generation | batch_69a90fcb8ca48190a9ee50559ba73b22 |
completed | March 5, 2026, 5:08 a.m. |
Created at: March 4, 2026, 7:27 p.m.