Triple
T36088291
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Marilyn Manson triptych |
E1043842
|
entity |
| Predicate | hasPartReleaseYear |
P97750
|
FINISHED |
| Object | Antichrist Superstar: 1996 |
—
|
NE NERFINISHED |
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: Antichrist Superstar: 1996 | Statement: [Marilyn Manson triptych, hasPartReleaseYear, Antichrist Superstar: 1996]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasPartReleaseYear Context triple: [Marilyn Manson triptych, hasPartReleaseYear, Antichrist Superstar: 1996]
-
A.
hasPartInYear
chosen
Indicates that something includes or contains a specific part, component, or segment that is associated with a particular year.
-
B.
eligibleReleaseYear
Indicates the year in which something qualifies or is permitted to be released according to specified criteria or rules.
-
C.
stableReleaseYear
Indicates the calendar year in which a stable, non-beta version of something (such as software or a product) was officially released.
-
D.
fullReleaseYear
Indicates the calendar year in which something is fully released or made publicly available in its complete form.
-
E.
workReleaseYearOfAppearance
Indicates the year in which a particular work was first released or made its initial appearance.
- 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_69f76e32d60c8190ba781ffaaab4aa3d |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_69fff59a00a881909b35b799654b3c45 |
completed | May 10, 2026, 3:03 a.m. |
| PD | Predicate disambiguation | batch_69fff4d0a2e081909c972189b33d0128 |
completed | May 10, 2026, 3 a.m. |
Created at: May 3, 2026, 4:08 p.m.