Triple
T37504985
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | September Dossier |
E932066
|
entity |
| Predicate | termUsedInMedia |
P119109
|
FINISHED |
| Object | sexed up dossier |
—
|
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: sexed up dossier | Statement: [September Dossier, termUsedInMedia, sexed up dossier]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: termUsedInMedia Context triple: [September Dossier, termUsedInMedia, sexed up dossier]
-
A.
commonlyUsedInMediaOf
Indicates that something is frequently employed or featured within a particular medium or type of media.
-
B.
usedInMediaAs
Indicates that something is employed, featured, or referenced within a media work (such as a film, show, game, or publication) in some capacity.
-
C.
usedInMediaOf
Indicates that something (e.g., a work, element, or content) is employed or appears within a particular media work or production.
-
D.
usedByMediaToReferTo
chosen
Indicates that a particular name, term, or label is employed by media sources to refer to a given entity.
-
E.
usedByMediaIn
Indicates that something is employed or utilized within a particular media work or medium.
- 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_69f76ec5268481909ea01c73aeeefd42 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_69fba68077788190b311e027435fcf87 |
completed | May 6, 2026, 8:37 p.m. |
| PD | Predicate disambiguation | batch_69fba34c65ac8190b298f0f00d1dcc0e |
completed | May 6, 2026, 8:23 p.m. |
Created at: May 3, 2026, 4:17 p.m.