Triple
T382365
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tinker Tailor Soldier Spy (2011 film) |
E8706
|
entity |
| Predicate | originalWorkPublicationYear |
P25
|
FINISHED |
| Object | 1974 |
—
|
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: 1974 | Statement: [Tinker Tailor Soldier Spy (2011 film), originalWorkPublicationYear, 1974]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: originalWorkPublicationYear Context triple: [Tinker Tailor Soldier Spy (2011 film), originalWorkPublicationYear, 1974]
-
A.
publicationYear
chosen
Indicates the specific calendar year in which a work was formally published or released.
-
B.
originYear
Indicates the year in which something first originated, was created, or began.
-
C.
publicationPeriod
Indicates the span of time during which something is published, active in publication, or valid as a published work.
-
D.
yearWorkWritten
Indicates the year in which a particular work was written or created.
-
E.
articulatedInDocumentYear
Indicates that something is expressed, stated, or formally presented in a document created or associated with a specific year.
- 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.