Triple
T27031024
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | RoadKill Cook-off |
E680916
|
entity |
| Predicate | judging |
P46345
|
FINISHED |
| Object | people’s choice voting |
—
|
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: people’s choice voting | Statement: [RoadKill Cook-off, judging, people’s choice voting]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: judging Context triple: [RoadKill Cook-off, judging, people’s choice voting]
-
A.
judgedBy
chosen
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.
judge
Indicates that one entity evaluates, forms an opinion about, or makes a decision regarding another entity or situation.
-
D.
judgedOn
Indicates that an entity is evaluated or assessed based on a specified criterion, standard, or aspect.
-
E.
judgeFrom
Indicates that one entity forms an opinion, evaluation, or conclusion about something based on another specified source, basis, or perspective.
- 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_69eeeb5566f08190813daf896fa3da04 |
completed | April 27, 2026, 4:51 a.m. |
| NER | Named-entity recognition | batch_69f622361b9c81908120e48259c211a1 |
completed | May 2, 2026, 4:11 p.m. |
| PD | Predicate disambiguation | batch_69f620e0b37481909a280574decbd443 |
completed | May 2, 2026, 4:05 p.m. |
Created at: April 27, 2026, 7:13 a.m.