Triple
T4452297
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Frank Money |
E97640
|
entity |
| Predicate | createdInWorkPublicationYear |
P25
|
FINISHED |
| Object | 2012 |
—
|
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: 2012 | Statement: [Frank Money, createdInWorkPublicationYear, 2012]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: createdInWorkPublicationYear Context triple: [Frank Money, createdInWorkPublicationYear, 2012]
-
A.
publicationYear
chosen
Indicates the specific calendar year in which a work was formally published or released.
-
B.
lastPublicationYear
Indicates the year in which an entity’s most recent publication was released.
-
C.
firstPublicationPeriod
Indicates the time span during which something was first published or initially made publicly available.
-
D.
laterCollectionPublicationYear
Indicates that the referenced collection was published in a year later than the year associated with the compared collection or work.
-
E.
serialPublicationStartYear
Indicates the calendar year in which a serial publication (such as a journal, magazine, or series) first began being issued.
- 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_69b3454777808190b78aa9047ba1f018 |
completed | March 12, 2026, 10:59 p.m. |
| NER | Named-entity recognition | batch_69b355f3731c81909cc5a782b12ddd38 |
completed | March 13, 2026, 12:10 a.m. |
| PD | Predicate disambiguation | batch_69b34f649df081909d3cc2f6a1b8f282 |
completed | March 12, 2026, 11:42 p.m. |
Created at: March 12, 2026, 11:33 p.m.