Triple
T32991205
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Gauge-invariant cosmological perturbations |
E844091
|
entity |
| Predicate | hasNamedConcept |
P531
|
FINISHED |
| Object | Bardeen potentials |
—
|
NE NERFINISHED |
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: Bardeen potentials | Statement: [Gauge-invariant cosmological perturbations, hasNamedConcept, Bardeen potentials]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasNamedConcept Context triple: [Gauge-invariant cosmological perturbations, hasNamedConcept, Bardeen potentials]
-
A.
hasConcept
chosen
Indicates that an entity includes, embodies, or is associated with a particular concept.
-
B.
isNamedEntity
Indicates that the subject is recognized as a named entity, such as a specific person, organization, location, or other proper noun.
-
C.
hasNaming
Indicates that one entity assigns, bears, or is associated with a specific name or designation provided by another entity.
-
D.
hasNamedForRole
Indicates that an entity has been given a specific name or label that corresponds to a particular role it plays.
-
E.
hasImplementedConcept
Indicates that an entity has put a particular concept into practice or realized it in an implemented form.
- 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_69f3494d99988190b502c68926af2c4d |
completed | April 30, 2026, 12:21 p.m. |
| NER | Named-entity recognition | batch_69feba0f09508190b3e871c62b19ec7f |
completed | May 9, 2026, 4:37 a.m. |
| PD | Predicate disambiguation | batch_69feb957fe7c8190969fb31a6d1a59c8 |
completed | May 9, 2026, 4:34 a.m. |
Created at: May 1, 2026, 1:22 a.m.