Triple
T26114792
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Harvey Specter |
E658794
|
entity |
| Predicate | styleTrait |
P106662
|
FINISHED |
| Object | tailored suits |
—
|
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: tailored suits | Statement: [Harvey Specter, styleTrait, tailored suits]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: styleTrait Context triple: [Harvey Specter, styleTrait, tailored suits]
-
A.
styleTendsTo
Indicates that one style is generally inclined or likely to develop, appear, or be adopted in the direction of another style.
-
B.
styleDetail
chosen
Indicates a relationship where specific stylistic characteristics or attributes of something are described or specified in detail.
-
C.
styleFor
Indicates a relationship where one entity defines, specifies, or is used as the style or styling configuration applied to another entity.
-
D.
styleSpecialty
Indicates a relationship where an entity’s expertise, focus, or specialization is in a particular style or stylistic approach.
-
E.
styleCategory
Indicates the stylistic classification or genre category that an item, work, or entity belongs to.
- 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_69ee5bc20298819099a42be042eb2349 |
completed | April 26, 2026, 6:38 p.m. |
| NER | Named-entity recognition | batch_69f60ac643108190ae81561267155791 |
completed | May 2, 2026, 2:31 p.m. |
| PD | Predicate disambiguation | batch_69f5b0021da88190bdd4cf2698c23edf |
completed | May 2, 2026, 8:04 a.m. |
Created at: April 26, 2026, 8:04 p.m.