Triple
T20690404
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | SO(32) heterotic string theory |
E508535
|
entity |
| Predicate | containsAntisymmetricTensor |
P141071
|
FINISHED |
| Object | true |
—
|
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: true | Statement: [SO(32) heterotic string theory, containsAntisymmetricTensor, true]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: containsAntisymmetricTensor Context triple: [SO(32) heterotic string theory, containsAntisymmetricTensor, true]
-
A.
bracketIsAntisymmetric
Indicates that the bracket operation changes sign when its two arguments are swapped, so [x, y] = −[y, x].
-
B.
isSkewSymmetric
Indicates that a relation or matrix changes sign when its arguments or indices are swapped, i.e., R(x, y) = −R(y, x), with all diagonal/self-relations being zero.
-
C.
hasExchangeSymmetry
Indicates that a relationship or configuration remains unchanged when the positions or roles of the involved entities are interchanged.
-
D.
isSymmetric
Indicates that a relationship holds in both directions between two entities, so if it applies from A to B, it also applies from B to A.
-
E.
isLorentzCovariant
Indicates that the quantity or equation preserves its form under Lorentz transformations between inertial reference frames.
- 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_69e0b4c1ed408190b72dd26b1e33f8a1 |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e6c10cb5588190acb88f2c82fc593a |
completed | April 21, 2026, 12:13 a.m. |
| PD | Predicate disambiguation | batch_69e5c03caee881908be4dd25796a03d5 |
completed | April 20, 2026, 5:57 a.m. |
| PDg | Predicate description generation | batch_69e5c3caef50819093c8159fe8d6435b |
completed | April 20, 2026, 6:12 a.m. |
Created at: April 16, 2026, 12:08 p.m.