Triple
T15872748
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Prefontaine |
E384869
|
entity |
| Predicate | starring |
P1507
|
FINISHED |
| Object | Laurel Holloman |
E540759
|
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: Laurel Holloman | Statement: [Prefontaine, starring, Laurel Holloman]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Laurel Holloman Context triple: [Prefontaine, starring, Laurel Holloman]
-
A.
Laurel Holloman
chosen
Laurel Holloman is an American actress best known for her role as Tina Kennard on the groundbreaking LGBTQ+ television drama "The L Word."
-
B.
Mary Beth Peil
Mary Beth Peil is an American actress and singer known for her work on Broadway, in film and television, and for originating prominent roles in major stage productions.
-
C.
Lou Ann Barton
Lou Ann Barton is an American blues singer known for her powerful vocals and work in the Austin, Texas music scene, including collaborations with Stevie Ray Vaughan and other prominent blues artists.
-
D.
Eileen Morrow
Eileen Morrow is a person notable enough to be recognized as a significant bearer of the surname Morrow.
-
E.
Jane Loring
Jane Loring was a film editor known for her work in early 20th-century American cinema.
- 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_69d86da4e86481909f1325fdc971b5ec |
completed | April 10, 2026, 3:25 a.m. |
| NER | Named-entity recognition | batch_69e155faefd08190af634867370796b3 |
completed | April 16, 2026, 9:34 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ffb041adac8190a8e6e5c646fdedf3 |
completed | May 9, 2026, 10:08 p.m. |
Created at: April 10, 2026, 4:51 a.m.