Triple
T26375962
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | FRPS |
E660897
|
entity |
| Predicate | categoryVariants |
P113983
|
FINISHED |
| Object | Fellowship in different RPS specialist areas |
—
|
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: Fellowship in different RPS specialist areas | Statement: [FRPS, categoryVariants, Fellowship in different RPS specialist areas]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: categoryVariants Context triple: [FRPS, categoryVariants, Fellowship in different RPS specialist areas]
-
A.
productVariant
Indicates that one entity is a specific variant or version of a more general product entity.
-
B.
hasVariantsIn
chosen
Indicates that an entity exists in multiple alternative forms or versions within a specified context or set.
-
C.
styleVariants
Indicates that an entity has alternative stylistic forms or versions related to it.
-
D.
returnVariants
Indicates that one entity provides or yields alternative forms, versions, or options of another entity.
-
E.
brandNameVariant
Indicates that one brand name is an alternative or variant form of another brand name, such as a spelling, regional, or stylistic variation.
- 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_69ee812a698881908d6a58265995fa39 |
completed | April 26, 2026, 9:18 p.m. |
| NER | Named-entity recognition | batch_69f6106f23cc8190854556a454648ab0 |
completed | May 2, 2026, 2:55 p.m. |
| PD | Predicate disambiguation | batch_69f602d2ec748190ae95154f34c7878f |
completed | May 2, 2026, 1:57 p.m. |
Created at: April 26, 2026, 11:01 p.m.