Triple
T29340626
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Manuel Calavera |
E744025
|
entity |
| Predicate | remasteredAppearance |
P100031
|
FINISHED |
| Object | Grim Fandango Remastered |
—
|
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: Grim Fandango Remastered | Statement: [Manuel Calavera, remasteredAppearance, Grim Fandango Remastered]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: remasteredAppearance Context triple: [Manuel Calavera, remasteredAppearance, Grim Fandango Remastered]
-
A.
hasRemasteredAppearanceIn
chosen
Indicates that an entity appears in a remastered version of a work or medium.
-
B.
remasteredVersion
Indicates that one entity is a newly produced, higher-quality audio or visual version of another original recording or release.
-
C.
remasteredAt
Indicates that an existing work has been reprocessed or updated at a specific time or in a specific release to improve its quality or presentation.
-
D.
remakeAppearance
Indicates that one entity creates a new version or updated form of another entity’s appearance.
-
E.
remasteredByTeamMember
Indicates that a work has been remastered by a specific member of a team.
- 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_69f09126cfcc8190899b16fbf3c2bf7b |
completed | April 28, 2026, 10:51 a.m. |
| NER | Named-entity recognition | batch_69f66d7765208190b87b1cc6d96a151c |
completed | May 2, 2026, 9:32 p.m. |
| PD | Predicate disambiguation | batch_69f66abfdaf08190a55f14c70be6fd4d |
completed | May 2, 2026, 9:21 p.m. |
Created at: April 28, 2026, 1:33 p.m.