Triple
T4714990
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Michael Barrett |
E104613
|
entity |
| Predicate | notableWork |
P4
|
FINISHED |
| Object | One on One |
E249025
|
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: One on One | Statement: [Michael Barrett, notableWork, One on One]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: One on One Context triple: [Michael Barrett, notableWork, One on One]
-
A.
One on One
chosen
One on One is an American television sitcom that follows a sportscaster who becomes a full-time single father to his teenage daughter, blending family comedy with coming-of-age themes.
-
B.
One on One
One on One is a novel by American author Tabitha King, known for its exploration of complex personal relationships and small-town life.
-
C.
The Only One
"The Only One" is a song by Lionel Richie from his hit 1983 album "Can't Slow Down."
-
D.
One and Only
"One and Only" is a song by Mariah Carey from her 2005 album *The Emancipation of Mimi*.
-
E.
Once Again
"Once Again" is a song featured on the album "Show Me."
- 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_69bd43ec4a348190bc41afae43375e71 |
completed | March 20, 2026, 12:56 p.m. |
| NER | Named-entity recognition | batch_69bd6408dc5c8190a8d6b1c1a3eba2df |
completed | March 20, 2026, 3:13 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69be108002e08190b13856f2af135bfc |
completed | March 21, 2026, 3:29 a.m. |
Created at: March 20, 2026, 1:18 p.m.