Triple
T37159312
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sterling Cooper |
E920601
|
entity |
| Predicate | hasAccountExecutive |
P146552
|
FINISHED |
| Object | Pete Campbell |
—
|
NE NERFINISHED |
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: Pete Campbell | Statement: [Sterling Cooper, hasAccountExecutive, Pete Campbell]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasAccountExecutive Context triple: [Sterling Cooper, hasAccountExecutive, Pete Campbell]
-
A.
hasExecutivePartner
Indicates that an entity has a business partner with executive-level authority or status within the partnership.
-
B.
hasBusinessAdministrator
Indicates that an entity is associated with another entity that serves as its business administrator, responsible for managing its business-related operations or affairs.
-
C.
headOfAccount
chosen
Indicates that one entity serves as the primary responsible authority or leader for a specified account.
-
D.
hasMarketingRole
Indicates that an entity holds a position or responsibility related to marketing activities within an organization.
-
E.
containsAccountOf
Indicates that one entity includes, records, or holds information about another entity’s account.
- 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_69f76ea0429081908c711b55599eac3c |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_69fd2839880c819099a7a89783f2270e |
completed | May 8, 2026, 12:03 a.m. |
| PD | Predicate disambiguation | batch_69fd23dc5da48190ae8ba08947d34956 |
completed | May 7, 2026, 11:44 p.m. |
Created at: May 3, 2026, 4:15 p.m.