Triple
T37159924
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sterling family (Mad Men) |
E920619
|
entity |
| Predicate | primaryRepresentative |
P205767
|
FINISHED |
| Object | Roger Sterling |
E268673
|
NE 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: Roger Sterling | Statement: [Sterling family (Mad Men), primaryRepresentative, Roger Sterling]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: primaryRepresentative Context triple: [Sterling family (Mad Men), primaryRepresentative, Roger Sterling]
-
A.
primaryLegalRepresentative
Indicates that one entity serves as the main authorized legal representative or agent acting on behalf of another entity in legal matters.
-
B.
primaryOfficer
Indicates that an entity serves as the main or leading officer responsible for another entity or organization.
-
C.
primaryParticipant
Indicates that an entity plays the main or most central role in a given event, activity, or relationship.
-
D.
primaryReferent
Indicates that one entity is the main or most salient referent associated with another entity among potentially multiple candidates.
-
E.
primaryPeople
Indicates that the referenced people are the main or most important individuals associated with a given entity, event, or context.
- F. None of above. chosen
Provenance (5 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_6a037cad051c8190b28b354b89208574 |
completed | May 12, 2026, 7:17 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a40f1638290819099a14dabd62a7ef5 |
completed | June 28, 2026, 10:03 a.m. |
| PD | Predicate disambiguation | batch_6a037a11efc08190bb7cacc1325b4dc6 |
completed | May 12, 2026, 7:05 p.m. |
| PDg | Predicate description generation | batch_6a037c842b2c819082f1d2db995ac2eb |
completed | May 12, 2026, 7:16 p.m. |
Created at: May 3, 2026, 4:15 p.m.