Triple
T382023
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Pride and Prejudice (1995 TV series) |
E8700
|
entity |
| Predicate | releaseFormat |
P5095
|
FINISHED |
| Object | television broadcast |
—
|
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: television broadcast | Statement: [Pride and Prejudice (1995 TV series), releaseFormat, television broadcast]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: releaseFormat Context triple: [Pride and Prejudice (1995 TV series), releaseFormat, television broadcast]
-
A.
releaseType
Indicates the kind or category of a release event or version associated with an entity.
-
B.
releaseForm
Indicates that one entity formally authorizes the release or disclosure of information, rights, or responsibilities to another entity through a consent or waiver document.
-
C.
releaseStatus
Indicates the current state or phase of an item’s release process (e.g., planned, in progress, or completed).
-
D.
format
Indicates the specific arrangement, structure, or presentation style in which something is organized or expressed.
-
E.
releaseChannel
chosen
Indicates the distribution pathway or medium through which something (such as a product, update, or content) is made available or delivered to its recipients.
- 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_69a2e7f47dd08190a4e294ccbbe46cd4 |
completed | Feb. 28, 2026, 1:04 p.m. |
| NER | Named-entity recognition | batch_69a2ec2e3d5c8190b358bd9fd6b16a14 |
completed | Feb. 28, 2026, 1:22 p.m. |
| PD | Predicate disambiguation | batch_69a2e96602188190b0cbc167f55a9237 |
completed | Feb. 28, 2026, 1:11 p.m. |
Created at: Feb. 28, 2026, 1:08 p.m.