Triple
T37159310
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sterling Cooper |
E920601
|
entity |
| Predicate | hasOfficeManager |
P2962
|
FINISHED |
| Object | Joan Holloway |
—
|
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: Joan Holloway | Statement: [Sterling Cooper, hasOfficeManager, Joan Holloway]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasOfficeManager Context triple: [Sterling Cooper, hasOfficeManager, Joan Holloway]
-
A.
hasTopOffice
Indicates that an entity holds the highest-ranking office or position within a specified organization, institution, or jurisdiction.
-
B.
employedByBranchManager
Indicates that one entity works as an employee under the authority or supervision of a branch manager.
-
C.
hasOffice
Indicates that an entity possesses or maintains an office at a particular location or within a specific organization.
-
D.
manager
chosen
Indicates that one entity holds a supervisory or administrative role with authority and responsibility over another entity.
-
E.
hasAssociatedOffice
Indicates that an entity is linked to or connected with a particular office in an official or functional capacity.
- 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_69fd09840ea88190a2e6d7e577ade717 |
completed | May 7, 2026, 9:52 p.m. |
| PD | Predicate disambiguation | batch_69fd064c49988190afadddbd04d7cb94 |
completed | May 7, 2026, 9:38 p.m. |
Created at: May 3, 2026, 4:15 p.m.