Triple
T34438492
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Elevator to the Gallows |
E884033
|
entity |
| Predicate | releaseYearFrance |
P44452
|
FINISHED |
| Object | 1958 |
—
|
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: 1958 | Statement: [Elevator to the Gallows, releaseYearFrance, 1958]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: releaseYearFrance Context triple: [Elevator to the Gallows, releaseYearFrance, 1958]
-
A.
releaseDateFrance
chosen
Indicates the date on which something (such as a product, film, or work) was officially released in France.
-
B.
firstFrenchPerformanceYear
Indicates the year in which something (such as a work, event, or performance) was first performed in France.
-
C.
FrenchEditionPublicationYear
Indicates the year in which a French-language edition of a work was published.
-
D.
dateCededToFrance
Indicates the date on which control or sovereignty over an entity was formally transferred to France.
-
E.
usedByFrance
Indicates that something is utilized, employed, or operated by France as a country or its official institutions.
- 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_69f349c548d88190978e2a82502c03d0 |
completed | April 30, 2026, 12:23 p.m. |
| NER | Named-entity recognition | batch_69fce7671f108190bf3ebf54339068b5 |
completed | May 7, 2026, 7:26 p.m. |
| PD | Predicate disambiguation | batch_69fce5b5a84c81908ac1b5b9f08d48d0 |
completed | May 7, 2026, 7:19 p.m. |
Created at: May 1, 2026, 2 a.m.