Triple
T8270637
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | ladies' singles figure skating |
E193418
|
entity |
| Predicate | judgedOn |
P82415
|
FINISHED |
| Object | technical elements |
—
|
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: technical elements | Statement: [ladies' singles figure skating, judgedOn, technical elements]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: judgedOn Context triple: [ladies' singles figure skating, judgedOn, technical elements]
-
A.
judgedBy
Indicates that one entity evaluates, assesses, or forms an opinion about another entity, often in an official or critical capacity.
-
B.
judgedAs
Indicates that one entity evaluates or forms an opinion about another entity according to some criteria or standard.
-
C.
judgeFrom
Indicates that one entity forms an opinion, evaluation, or conclusion about something based on another specified source, basis, or perspective.
-
D.
seasonJudged
Indicates that a particular season has been evaluated or assessed, typically in terms of quality, performance, or outcome.
-
E.
judgesMayBe
Indicates that certain individuals can serve in the role of judges under specified conditions or classifications.
- 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_69ca82e14ae481908ffdb822cd2192bc |
completed | March 30, 2026, 2:04 p.m. |
| NER | Named-entity recognition | batch_69cb795243fc8190a66afef7476e1147 |
completed | March 31, 2026, 7:35 a.m. |
| PD | Predicate disambiguation | batch_69cb70a4525481909399d313a6247ace |
completed | March 31, 2026, 6:58 a.m. |
| PDg | Predicate description generation | batch_69cb76d648988190ab0669cc0592e827 |
completed | March 31, 2026, 7:25 a.m. |
Created at: March 30, 2026, 5:50 p.m.