Triple
T16053245
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hitch |
E389407
|
entity |
| Predicate | starring |
P1507
|
FINISHED |
| Object | Will Smith |
E140767
|
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: Will Smith | Statement: [Hitch, starring, Will Smith]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Will Smith Context triple: [Hitch, starring, Will Smith]
-
A.
Will Smith
chosen
Will Smith is an American actor, rapper, and film producer known for his charismatic performances in blockbuster films and television.
-
B.
Will Smith
Will Smith is a British television writer known for his work on comedy series such as "The Thick of It" and "Veep."
-
C.
J. B. Smoove
J. B. Smoove is an American comedian, actor, and writer best known for his energetic, improvisational style and his role as Leon Black on the HBO series "Curb Your Enthusiasm."
-
D.
Martin Lawrence
Martin Lawrence is an American comedian and actor best known for his energetic stand-up, his hit sitcom "Martin," and his leading roles in the "Bad Boys" film series alongside Will Smith.
-
E.
Cuba Gooding Jr.
Cuba Gooding Jr. is an American actor best known for his Academy Award–winning performance in "Jerry Maguire" and prominent roles in films such as "Boyz n the Hood" and "Men of Honor."
- 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_69d86dae698881908327ef2d67706cb9 |
completed | April 10, 2026, 3:25 a.m. |
| NER | Named-entity recognition | batch_69e1836365688190b182f29bbb66127e |
completed | April 17, 2026, 12:48 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ffe478bcc48190bdd4fcb7ec51caad |
completed | May 10, 2026, 1:50 a.m. |
Created at: April 10, 2026, 4:56 a.m.