Triple
T13811225
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Williams Lea |
E331893
|
entity |
| Predicate | targetFunction |
P23285
|
FINISHED |
| Object | corporate support functions |
—
|
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: corporate support functions | Statement: [Williams Lea, targetFunction, corporate support functions]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: targetFunction Context triple: [Williams Lea, targetFunction, corporate support functions]
-
A.
intendedFunction
Indicates that something is designed or purposed to perform a particular role, use, or function.
-
B.
assignedFunction
Indicates that a specific role, duty, or function has been formally allocated to an entity.
-
C.
associatedFunction
chosen
Indicates that one entity has a related or linked function that is conceptually or operationally connected to it.
-
D.
affectedFunction
Indicates that one entity has an impact on, alters, or impairs the operation or behavior of another entity’s function.
-
E.
transferFunction
Indicates a relationship where some quantity, property, or information is passed or conveyed from one entity to another.
- 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_69d81c59f8808190a851bc56afdc55e9 |
completed | April 9, 2026, 9:38 p.m. |
| NER | Named-entity recognition | batch_69de026ff6b481908066d6bf27064417 |
completed | April 14, 2026, 9:01 a.m. |
| PD | Predicate disambiguation | batch_69dbc862e9608190bd8a3d883959b7e4 |
completed | April 12, 2026, 4:29 p.m. |
Created at: April 9, 2026, 10:12 p.m.