Triple
T18527786
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Absorbing Man |
E452762
|
entity |
| Predicate | affiliation |
P10
|
FINISHED |
| Object | Lethal Legion |
—
|
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: Lethal Legion | Statement: [Absorbing Man, affiliation, Lethal Legion]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Lethal Legion Context triple: [Absorbing Man, affiliation, Lethal Legion]
-
A.
Lethal Legion
chosen
The Lethal Legion is a recurring team of supervillains in Marvel Comics, often assembled by powerful foes like Ultron to battle the Avengers.
-
B.
The Legionnaires
The Legionnaires is a documentary novel by Swedish author Per Olov Enquist that examines the controversial postwar extradition of Baltic soldiers from Sweden to the Soviet Union.
-
C.
Thundering Legion
The Thundering Legion was a Roman military unit later famed in Christian tradition for a miraculous storm said to have saved it during battle, known as the Miracle of the Rain.
-
D.
Legion of Doom
The Legion of Doom is a notorious supervillain team in DC Comics, typically composed of some of the Justice League’s greatest enemies who unite to oppose the heroes.
-
E.
Legion of Blue
Legion of Blue is the official student cheering section that supports Penn State Lady Lions basketball games.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69d8d387b5548190aa030dad2cb4947e |
completed | April 10, 2026, 10:40 a.m. |
| NER | Named-entity recognition | batch_69e533f9bd1081909743b24e290b7dfe |
completed | April 19, 2026, 7:58 p.m. |
Created at: April 10, 2026, 11:37 a.m.