Triple
T18474701
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Adrian Lester |
E451398
|
entity |
| Predicate | notableWork |
P4
|
FINISHED |
| Object | Undercover |
—
|
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: Undercover | Statement: [Adrian Lester, notableWork, Undercover]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Undercover Context triple: [Adrian Lester, notableWork, Undercover]
-
A.
Undercover
Undercover is a book by former CIA officer and Watergate conspirator E. Howard Hunt, detailing his experiences in espionage and covert operations.
-
B.
Undercover
chosen
Undercover is a British television drama series that follows a lawyer uncovering shocking secrets about her husband and the justice system.
-
C.
Undercover
"Undercover" is a song featured on the soundtrack album "Godzilla: The Album," released in conjunction with the 1998 film "Godzilla."
-
D.
Undercover
Undercover is a 1983 studio album by The Rolling Stones that blends rock with then-contemporary dance and new wave influences.
-
E.
Undercovers
Undercovers is an American action-spy television series created by J.J. Abrams that follows a married couple who are reactivated as CIA agents.
- 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_69d8d38465a0819099b9b42d2a662ac1 |
completed | April 10, 2026, 10:40 a.m. |
| NER | Named-entity recognition | batch_69e53062387481909d4503fc963f9913 |
completed | April 19, 2026, 7:43 p.m. |
Created at: April 10, 2026, 11:34 a.m.