Triple
T7499840
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Frozone |
E177228
|
entity |
| Predicate | realName |
P9233
|
FINISHED |
| Object | Lucius Best |
E236498
|
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: Lucius Best | Statement: [Frozone, realName, Lucius Best]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Lucius Best Context triple: [Frozone, realName, Lucius Best]
-
A.
Lucius Best
chosen
Lucius Best is a superhero known as Frozone, a close friend and ally of the Parr family in Pixar's animated film "The Incredibles."
-
B.
Lucas Beauchamp
Lucas Beauchamp is a proud, defiant Black farmer and central character in William Faulkner’s fiction, most notably in the novel "Go Down, Moses."
-
C.
Lucas Black
Lucas Black is an American actor best known for his roles in films such as "Sling Blade," "The Fast and the Furious: Tokyo Drift," and the football drama "Friday Night Lights."
-
D.
Sam Best
Sam Best is a relatively obscure individual whose name is noted primarily as a bearer of the surname Best.
-
E.
Tobias Vaughn
Tobias Vaughn is a villainous industrialist and secret ally of the Cybermen in the Doctor Who serial "The Invasion."
- 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_69c69f2696688190915a8458f2398211 |
completed | March 27, 2026, 3:15 p.m. |
| NER | Named-entity recognition | batch_69c6f598dfac8190a123daaac0784aee |
completed | March 27, 2026, 9:24 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c83c900ad081908506a2097f7fd30b |
completed | March 28, 2026, 8:39 p.m. |
Created at: March 27, 2026, 3:44 p.m.