Triple
T20690662
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Donaldson–Witten theory |
E508540
|
entity |
| Predicate | twistProduces |
P490
|
FINISHED |
| Object | scalar supercharge |
—
|
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: scalar supercharge | Statement: [Donaldson–Witten theory, twistProduces, scalar supercharge]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: twistProduces Context triple: [Donaldson–Witten theory, twistProduces, scalar supercharge]
-
A.
hasTwist
Indicates that an entity (such as a story, object, or feature) includes an unexpected change, reversal, or surprising element relative to what was previously established or anticipated.
-
B.
twistElement
Indicates that one entity applies a twisting or rotational deformation to another entity.
-
C.
twistCount
Indicates the number of twists or rotational turns applied or present in the relationship between the related entities.
-
D.
produces
chosen
Indicates that one entity creates, generates, or yields another entity as a result or output.
-
E.
twistOffAngle
Indicates the angular amount or orientation by which something is twisted off from its original or reference position.
- 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_69e0b4c1ed408190b72dd26b1e33f8a1 |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e6c10d83548190a52b9ef84c8f9205 |
completed | April 21, 2026, 12:13 a.m. |
| PD | Predicate disambiguation | batch_69e5c03caee881908be4dd25796a03d5 |
completed | April 20, 2026, 5:57 a.m. |
Created at: April 16, 2026, 12:08 p.m.