Triple
T7362176
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Deadpool |
E169776
|
entity |
| Predicate | ally |
P4662
|
FINISHED |
| Object | Wolverine |
E119393
|
NE 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: Wolverine | Statement: [Deadpool, ally, Wolverine]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Wolverine Context triple: [Deadpool, ally, Wolverine]
-
A.
Wolverine
Wolverine is a higher-speed Amtrak passenger train service that operates multiple daily routes between Chicago, Detroit, and Pontiac in the Midwestern United States.
-
B.
Wolverine
chosen
Wolverine is a popular Marvel Comics mutant superhero known for his retractable adamantium claws, accelerated healing factor, and membership in the X-Men.
-
C.
Wolverine Wildcat
Wolverine Wildcat is a classic wooden roller coaster located at the Michigan’s Adventure amusement park in Muskegon, Michigan.
-
D.
Magneto
Magneto is a powerful Marvel Comics supervillain and occasional antihero, known as a mutant with magnetic abilities and a complex ideological rivalry with the X-Men.
-
E.
The Wolverine
The Wolverine is a 2013 superhero film centered on the Marvel Comics character Wolverine, following his journey to Japan where he confronts both his past and powerful new enemies.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69c68a5ade988190885b7175f63b7534 |
completed | March 27, 2026, 1:47 p.m. |
| NER | Named-entity recognition | batch_69c6f15f218081909b5cc7a8cc695055 |
completed | March 27, 2026, 9:06 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c7fab3a9d88190b9193dd0729eba5a |
completed | March 28, 2026, 3:58 p.m. |
Created at: March 27, 2026, 3:06 p.m.