Triple
T12597644
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Queen for a Day |
E300772
|
entity |
| Predicate | presenter |
P83
|
FINISHED |
| Object | Jack Bailey |
E997441
|
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: Jack Bailey | Statement: [Queen for a Day, presenter, Jack Bailey]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Jack Bailey Context triple: [Queen for a Day, presenter, Jack Bailey]
-
A.
Jack Bailey
Jack Bailey is a fictional law enforcement officer who serves as the straight-laced partner to the reckless detective Dan Stark in the TV series "The Good Guys."
-
B.
Jack Bailey
chosen
Jack Bailey was an American radio and television personality best known for hosting the popular game show "Queen for a Day."
-
C.
Sean Bailey
Sean Bailey is an American film producer and studio executive known for overseeing major projects at Walt Disney Studios and producing acclaimed films such as "Gone Baby Gone."
-
D.
Sam Baldwin
Sam Baldwin is the widowed architect and devoted father portrayed by Tom Hanks in the romantic comedy film "Sleepless in Seattle."
-
E.
Edward Bailey
Edward Bailey is a retired MI6 agent and skilled operative portrayed by Anthony Hopkins in the action-comedy film "Red 2."
- 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_69d7bdea2ca881908f379526c13b1145 |
completed | April 9, 2026, 2:55 p.m. |
| NER | Named-entity recognition | batch_69d954cf33b88190bff339fcd3142cc8 |
completed | April 10, 2026, 7:51 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f67c6ddfdc81908df8baa701ed1fbf |
completed | May 2, 2026, 10:36 p.m. |
Created at: April 9, 2026, 5:08 p.m.