Triple
T14808288
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Underminer |
E348099
|
entity |
| Predicate | enemyOf |
P437
|
FINISHED |
| Object | Frozone |
E1083236
|
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: Frozone | Statement: [The Underminer, enemyOf, Frozone]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Frozone Context triple: [The Underminer, enemyOf, Frozone]
-
A.
Frozone
chosen
Frozone is a superhero from Pixar's "The Incredibles" franchise who can generate and manipulate ice, and is a close ally of the Parr family.
-
B.
Dr. Freeze
Dr. Freeze is a music producer best known for his work on R&B and pop hits, including collaborations with artists like Michael Jackson and Bell Biv DeVoe.
-
C.
Mr. Freeze
Mr. Freeze is a tragic Batman villain, a cryogenics expert whose body must be kept at subzero temperatures and who turns to cold-themed crime to save his terminally ill wife.
-
D.
Mr. Freeze
Mr. Freeze is a high-speed launched roller coaster themed after the Batman villain, known for its intense backward and forward runs through a twisted steel track.
-
E.
Larfleeze
Larfleeze is a DC Comics supervillain and the avaricious wielder of the orange light of greed, serving as the sole member of the Orange Lantern Corps.
- 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_69d822ea8b7c819097dfadf3d45545e6 |
completed | April 9, 2026, 10:06 p.m. |
| NER | Named-entity recognition | batch_69decf33b6a08190ab6a4cfeda2cc09c |
completed | April 14, 2026, 11:35 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fe64f6c6148190941b05d06d4dc54d |
completed | May 8, 2026, 10:34 p.m. |
Created at: April 10, 2026, 1:44 a.m.