Triple
T33929189
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jeff Fenech |
E869837
|
entity |
| Predicate | briefComebackYear |
P91011
|
FINISHED |
| Object | 2008 |
—
|
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: 2008 | Statement: [Jeff Fenech, briefComebackYear, 2008]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: briefComebackYear Context triple: [Jeff Fenech, briefComebackYear, 2008]
-
A.
madeComeback
Indicates that an entity returned to a previous level of success, performance, or prominence after a period of decline, absence, or setback.
-
B.
comebackEra
Indicates a period in which an entity returns to prominence or activity after a decline, hiatus, or setback.
-
C.
returnYear
Indicates the year in which something is returned or given back to its original owner, place, or state.
-
D.
comebackAlbumFor
Indicates that one album serves as an artist’s return or resurgence release following a period of inactivity, decline, or absence.
-
E.
revivalYear
chosen
Indicates the year in which something (such as a work, practice, or institution) was brought back into active use or renewed after a period of decline or inactivity.
- 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_69f3499a59788190bff762a891471b31 |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_69f7064e906881909c3186c646145d34 |
completed | May 3, 2026, 8:24 a.m. |
| PD | Predicate disambiguation | batch_69f70100ec1c8190a6b97f50e88891f2 |
completed | May 3, 2026, 8:02 a.m. |
Created at: May 1, 2026, 1:49 a.m.