Triple
T30917294
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | That Certain Woman |
E787614
|
entity |
| Predicate | previousVersionReleaseYear |
P91741
|
FINISHED |
| Object | 1918 |
—
|
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: 1918 | Statement: [That Certain Woman, previousVersionReleaseYear, 1918]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: previousVersionReleaseYear Context triple: [That Certain Woman, previousVersionReleaseYear, 1918]
-
A.
earlierVersionPublicationYear
Indicates that the associated value is the publication year of an earlier version of the described work.
-
B.
previousMajorRevisionYear
chosen
Indicates the calendar year in which the immediately preceding major revision or version of an item was released or finalized.
-
C.
bestKnownVersionReleaseYear
Indicates the calendar year in which the most widely recognized or prominent version of something was released.
-
D.
previousVersionInUseUntil
Indicates that an earlier version of something continued to be actively used up to a specified point in time.
-
E.
previousWorkReleaseYear
Indicates the year in which an earlier or prior work in a sequence or related set was released.
- 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_69f224bfaca88190b9d0dfcc86297fe9 |
completed | April 29, 2026, 3:33 p.m. |
| NER | Named-entity recognition | batch_69fe08d2b2e48190ac7be6d62d4a44a3 |
completed | May 8, 2026, 4:01 p.m. |
| PD | Predicate disambiguation | batch_69fe06cd3af08190ae25de0dc0cdd573 |
completed | May 8, 2026, 3:52 p.m. |
Created at: April 29, 2026, 8:51 p.m.