Triple
T4638848
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Rogers & Wells |
E101600
|
entity |
| Predicate | hasClientBase |
P53231
|
FINISHED |
| Object | corporate clients |
—
|
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 clients | Statement: [Rogers & Wells, hasClientBase, corporate clients]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasClientBase Context triple: [Rogers & Wells, hasClientBase, corporate clients]
-
A.
hasClient
Indicates that an entity maintains a client relationship with another entity, typically as a provider of goods or services.
-
B.
hasSupportBase
Indicates that one entity serves as the supporting base or foundation upon which another entity rests, is mounted, or is structurally stabilized.
-
C.
hasClientGroup
chosen
Indicates that an entity is associated with, or belongs to, a particular group of clients.
-
D.
hasResourceBase
Indicates that one entity possesses, is founded on, or derives from another entity serving as its fundamental resource or base.
-
E.
hasBaseIndex
Indicates that one entity serves as the reference or starting index from which another entity’s position, offset, or ordering is calculated.
- 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_69bd43d3bc7c81908f81fcf380476b0f |
completed | March 20, 2026, 12:55 p.m. |
| NER | Named-entity recognition | batch_69bd5a8e0ee88190becab97d2ef1571a |
completed | March 20, 2026, 2:32 p.m. |
| PD | Predicate disambiguation | batch_69bd5234d24c819095c79890b70eff9a |
completed | March 20, 2026, 1:57 p.m. |
Created at: March 20, 2026, 1:13 p.m.