Triple
T37159314
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sterling Cooper |
E920601
|
entity |
| Predicate | hasMediaDepartmentHead |
P42656
|
FINISHED |
| Object | Harry Crane |
—
|
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: Harry Crane | Statement: [Sterling Cooper, hasMediaDepartmentHead, Harry Crane]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasMediaDepartmentHead Context triple: [Sterling Cooper, hasMediaDepartmentHead, Harry Crane]
-
A.
musicDepartmentHead
Indicates that one entity serves as the head or leader of the music department of another entity.
-
B.
soundDepartmentHead
Indicates that one entity serves as the head or chief person in charge of the sound department for the other entity (such as a film, show, or production).
-
C.
hasHeadOf
chosen
Indicates that one entity serves as the leader, chief, or person in charge of another entity (such as an organization, group, or department).
-
D.
hasMediaMinistry
Indicates that an entity operates, oversees, or is associated with a ministry or department responsible for media-related affairs.
-
E.
headOfGovernmentDepartment
Indicates that one entity serves as the leader or chief official in charge of a particular government department.
- 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_69ff7eb7189c81909a8f73fbc4c48e02 |
completed | May 9, 2026, 6:36 p.m. |
| PD | Predicate disambiguation | batch_69ff7e54e11081908fb5ce10c5aa7b53 |
completed | May 9, 2026, 6:35 p.m. |
Created at: May 3, 2026, 4:15 p.m.