Triple
T29694161
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | M2-branes |
E751296
|
entity |
| Predicate | chargeQuantizedBy |
P147445
|
FINISHED |
| Object | integral of G_4 flux |
—
|
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: integral of G_4 flux | Statement: [M2-branes, chargeQuantizedBy, integral of G_4 flux]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: chargeQuantizedBy Context triple: [M2-branes, chargeQuantizedBy, integral of G_4 flux]
-
A.
chargeStoredProportionalTo
Indicates that the amount of charge stored in one entity varies in direct proportion to a specified quantity or property of another entity.
-
B.
chargedIn
Indicates that a legal charge or accusation against an entity was formally filed or brought in a particular jurisdiction, court, or case.
-
C.
charge
Indicates that one entity formally accuses another of an offense or imposes a financial cost or obligation on them.
-
D.
hasChargeQuantizationLabeledBy
chosen
Indicates that the charge quantization of one entity is specified or categorized using another entity as its label or classifier.
-
E.
chargedOn
Indicates that a fee, cost, or financial amount is applied to an account, entity, or transaction at a specific time or in connection with a particular event.
- 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_69f0d625b09481909b0b69aea1e846c8 |
completed | April 28, 2026, 3:45 p.m. |
| NER | Named-entity recognition | batch_69f672af46e48190b76e9298e7d23eef |
completed | May 2, 2026, 9:54 p.m. |
| PD | Predicate disambiguation | batch_69f6659f246081909821c5f452d14e8f |
completed | May 2, 2026, 8:59 p.m. |
Created at: April 28, 2026, 7:19 p.m.