Triple
T7160090
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Vice President of South Carolina |
E166919
|
entity |
| Predicate | officeTitleStyle |
P20993
|
FINISHED |
| Object | Vice President |
—
|
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: Vice President | Statement: [Vice President of South Carolina, officeTitleStyle, Vice President]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: officeTitleStyle Context triple: [Vice President of South Carolina, officeTitleStyle, Vice President]
-
A.
officeStyle
Indicates a stylistic or design relationship where one entity’s style is characterized as “office” or suitable for an office environment.
-
B.
titleHolderStyle
Indicates the manner or format in which a title holder’s status or designation is presented or styled in relation to another entity.
-
C.
officeHolderStyle
chosen
Indicates the formal title, manner of address, or stylistic designation used for a person holding a particular office or position.
-
D.
includesTitleStyle
Indicates that one entity incorporates or specifies a particular style or formatting for a title associated with it.
-
E.
titleVariant
Indicates that one title is an alternative or variant form of another title referring to the same work or entity.
- 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_69c68887a5cc8190bec0ea96227164f7 |
completed | March 27, 2026, 1:39 p.m. |
| NER | Named-entity recognition | batch_69c6e811d6b081909dafeee1d820c74f |
completed | March 27, 2026, 8:26 p.m. |
| PD | Predicate disambiguation | batch_69c6e1cd5c948190a9113b23f7308c21 |
completed | March 27, 2026, 8 p.m. |
Created at: March 27, 2026, 2:47 p.m.