Triple
T23515414
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Get Smart |
E574346
|
entity |
| Predicate | character |
P662
|
FINISHED |
| Object | Agent 99 |
—
|
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: Agent 99 | Statement: [Get Smart, character, Agent 99]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Agent 99 Context triple: [Get Smart, character, Agent 99]
-
A.
Agent 99
chosen
Agent 99 is the intelligent, resourceful female secret agent and partner to Maxwell Smart in the classic spy-comedy television series "Get Smart."
-
B.
Agent 9
Agent 9 is a hyperactive, gun-toting anthropomorphic character from the Spyro video game series who assists Spyro on various missions.
-
C.
Agent 86
Agent 86 is the bumbling yet resourceful secret agent protagonist of the classic satirical spy television series "Get Smart."
-
D.
Agent 13
Agent 13 is the codename of Sharon Carter, a highly skilled S.H.I.E.L.D. operative and frequent ally of Captain America in Marvel Comics.
-
E.
Agent 13
Agent 13 is an unproduced film script centered on a mysterious spy character, known primarily within industry and fan circles for its unrealized cinematic potential.
- 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_69e245bb3dcc8190ba9a2b35972b58d0 |
completed | April 17, 2026, 2:37 p.m. |
| NER | Named-entity recognition | batch_69f1aa81ab4c8190b85c8f80754020ea |
completed | April 29, 2026, 6:51 a.m. |
Created at: April 17, 2026, 6:08 p.m.