Triple
T26765450
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | up quark |
E674924
|
entity |
| Predicate | chargeConjugate |
P3975
|
FINISHED |
| Object | anti-up quark |
—
|
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: anti-up quark | Statement: [up quark, chargeConjugate, anti-up quark]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: chargeConjugate Context triple: [up quark, chargeConjugate, anti-up quark]
-
A.
hasChargeConjugation
chosen
Indicates that one entity is the charge-conjugated counterpart (particle vs. antiparticle form) of another entity.
-
B.
chargeConjugationEigenstate
Indicates that a particle or state is an eigenstate of the charge conjugation operator, meaning it transforms into itself up to a definite eigenvalue under charge conjugation.
-
C.
chargeParity
Indicates that two related entities share the same electric charge sign (parity), such as both being positively or both negatively charged.
-
D.
chargeCarrier
Indicates that an entity functions as the primary carrier of electric charge in or for another entity.
-
E.
conjugate
Indicates that one entity is a grammatical or mathematical counterpart of another, linked by a specific transformation such as verb inflection or complex-number pairing.
- 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_69eecda85298819097ee1c38a3d772e7 |
completed | April 27, 2026, 2:44 a.m. |
| NER | Named-entity recognition | batch_69f6192758648190ba2c0bfc9904994e |
completed | May 2, 2026, 3:32 p.m. |
| PD | Predicate disambiguation | batch_69f611ad2eb48190ac1ed0090f13f7a9 |
completed | May 2, 2026, 3:01 p.m. |
Created at: April 27, 2026, 3:59 a.m.