Triple
T20178784
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | ¡Dos! |
E492669
|
entity |
| Predicate | hasTrack |
P3284
|
FINISHED |
| Object | Lady Cobra |
—
|
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: Lady Cobra | Statement: [¡Dos!, hasTrack, Lady Cobra]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Lady Cobra Context triple: [¡Dos!, hasTrack, Lady Cobra]
-
A.
Lady Cobra
chosen
Lady Cobra is a fictional character from the comic series "¡Dos!" known for her distinctive, cobra-themed persona.
-
B.
Cobra La
Cobra La is a secretive, ancient civilization and splinter faction in the G.I. Joe universe that serves as a mystical, bio-organic counterpart to the technologically driven Cobra organization.
-
C.
Scorpion
Scorpion is an American television drama series that follows a team of brilliant misfits who tackle high-tech threats for the U.S. government.
-
D.
Scorpion
Scorpion is a thrill ride attraction in the Pantopia section of Busch Gardens Tampa Bay, known for its intense looping roller coaster experience.
-
E.
Scorpion
Scorpion is a vengeful undead ninja and one of the most iconic and enduring fighters in the Mortal Kombat video game series.
- 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_69da6268a034819081cbd9ea5a1c9475 |
completed | April 11, 2026, 3:02 p.m. |
| NER | Named-entity recognition | batch_69e668ed07c8819091bd9ffda237a91c |
completed | April 20, 2026, 5:57 p.m. |
Created at: April 11, 2026, 11:36 p.m.