Triple
T11344510
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Fashion of Mad Men |
E268679
|
entity |
| Predicate | usesAsReference |
P8581
|
FINISHED |
| Object | episodes of Mad Men |
—
|
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: episodes of Mad Men | Statement: [The Fashion of Mad Men, usesAsReference, episodes of Mad Men]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: usesAsReference Context triple: [The Fashion of Mad Men, usesAsReference, episodes of Mad Men]
-
A.
isUsedAs
Indicates that one entity serves a particular function, role, or purpose as another entity.
-
B.
isReferencedIn
chosen
Indicates that one entity is cited, mentioned, or otherwise referred to within another entity.
-
C.
usedAsSourceIn
Indicates that something serves as the origin, basis, or input from which another thing is derived, produced, or obtained.
-
D.
usedReferenceFrame
Indicates that one entity adopts or relies on another entity as the coordinate system or reference frame for describing positions, motions, or measurements.
-
E.
definesUseOf
Indicates that one entity specifies or determines how another entity is to be used or applied.
- 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_69d6aacbe18081909e5fadb50082dd96 |
completed | April 8, 2026, 7:21 p.m. |
| NER | Named-entity recognition | batch_69d80148e2048190a716b515d78efdd1 |
completed | April 9, 2026, 7:43 p.m. |
| PD | Predicate disambiguation | batch_69d7e6f8aeb4819080476f16a69b2ee3 |
completed | April 9, 2026, 5:50 p.m. |
Created at: April 8, 2026, 9:33 p.m.