Triple
T27529106
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Punxsutawney Phil |
E694918
|
entity |
| Predicate | predictionRule |
P160560
|
FINISHED |
| Object | no shadow means early spring |
—
|
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: no shadow means early spring | Statement: [Punxsutawney Phil, predictionRule, no shadow means early spring]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: predictionRule Context triple: [Punxsutawney Phil, predictionRule, no shadow means early spring]
-
A.
predictionType
Indicates the kind or category of prediction being made about an entity or event.
-
B.
predictionBy
Indicates that one entity serves as the source or author of a prediction made about another entity or outcome.
-
C.
predictionAlgorithm
Indicates a relationship where an algorithm generates predictions or forecasts about outcomes based on input data or observed patterns.
-
D.
predictedIn
Indicates that something has been forecast, anticipated, or estimated to occur within or as part of a specified context, time, or situation.
-
E.
predictionInterpretation
chosen
Indicates that one entity represents an explanation, meaning, or understanding of a prediction made about another entity.
- 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_69ef538608b081908b9f659bb09d5e0f |
completed | April 27, 2026, 12:16 p.m. |
| NER | Named-entity recognition | batch_69f62f31e12c8190880b758fef6a07e0 |
completed | May 2, 2026, 5:06 p.m. |
| PD | Predicate disambiguation | batch_69f62c1762f881908c25e8f70ecd5041 |
completed | May 2, 2026, 4:53 p.m. |
Created at: April 27, 2026, 1:25 p.m.