Triple
T23731455
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Pledis Entertainment |
E586418
|
entity |
| Predicate | hasNotableSubUnit |
P71417
|
FINISHED |
| Object | Orange Caramel |
—
|
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: Orange Caramel | Statement: [Pledis Entertainment, hasNotableSubUnit, Orange Caramel]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasNotableSubUnit Context triple: [Pledis Entertainment, hasNotableSubUnit, Orange Caramel]
-
A.
hasSubunits
chosen
Indicates that an entity is composed of or organized into smaller constituent units that are part of its structure.
-
B.
hasSubunitName
Indicates that an entity includes or is associated with a named subunit or component as part of its structure or organization.
-
C.
hasNotableSubtribe
Indicates that an entity (typically a larger tribal or ethnic group) includes a particular subtribe that is especially recognized or notable.
-
D.
subunitOf
Indicates that one entity functions as a component or smaller part within the structure or organization of another, larger entity.
-
E.
hasSubdivision
Indicates that one entity is divided into and contains another entity as one of its constituent parts or administrative units.
- 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_69e24907dc9c8190be074c9c96a0ec2d |
completed | April 17, 2026, 2:51 p.m. |
| NER | Named-entity recognition | batch_69f1b9193b14819096f1c7b11a441569 |
completed | April 29, 2026, 7:54 a.m. |
| PD | Predicate disambiguation | batch_69f155e4b1148190836ede4741dcb888 |
completed | April 29, 2026, 12:50 a.m. |
Created at: April 17, 2026, 7:09 p.m.