Triple
T26088690
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Merc with a Mouth |
E658057
|
entity |
| Predicate | appliedToUniverse |
P41009
|
FINISHED |
| Object | Marvel Universe |
—
|
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: Marvel Universe | Statement: [The Merc with a Mouth, appliedToUniverse, Marvel Universe]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: appliedToUniverse Context triple: [The Merc with a Mouth, appliedToUniverse, Marvel Universe]
-
A.
associatedUniverse
chosen
Indicates that one entity is linked or belongs to a particular universe, realm, or overarching world context.
-
B.
inUniverseUse
Indicates that something is used or occurs within a particular fictional or conceptual universe, as opposed to in the real world or another setting.
-
C.
underlyingUniverse
Indicates that one entity serves as the fundamental domain, space, or base structure within which the other entity is defined or operates.
-
D.
isUniversalFor
Indicates that a property, rule, or condition holds true for all members of a specified set or domain without exception.
-
E.
isUniversalFor
Indicates that something applies to or is valid for all members of a given set, domain, or context without exception.
- 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_69ee5bbfc4d08190a1b206d0ac3a1e8d |
completed | April 26, 2026, 6:38 p.m. |
| NER | Named-entity recognition | batch_69f6bbf6e33c819086e5176d64e7a614 |
completed | May 3, 2026, 3:07 a.m. |
| PD | Predicate disambiguation | batch_69f6ba6b1e6c8190adf9d6a257e0b744 |
completed | May 3, 2026, 3 a.m. |
Created at: April 26, 2026, 7:45 p.m.