Triple
T17920899
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Politician |
E448062
|
entity |
| Predicate | star |
P23405
|
FINISHED |
| Object | Laura Dreyfuss |
—
|
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: Laura Dreyfuss | Statement: [The Politician, star, Laura Dreyfuss]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Laura Dreyfuss Context triple: [The Politician, star, Laura Dreyfuss]
-
A.
Laura Dreyfuss
chosen
Laura Dreyfuss is an American actress and singer best known for her work in musical theatre and television, including roles on Broadway and in the TV series "Glee."
-
B.
Wendy Harris
Wendy Harris is a character known for being the mother figure in the context of the work in which she appears.
-
C.
Madeline Manning
Madeline Manning is an American middle-distance runner and Olympic gold medalist renowned for her achievements in the 800 meters.
-
D.
Susan Silver
Susan Silver is an American music manager best known for managing prominent Seattle grunge bands such as Soundgarden and Alice in Chains.
-
E.
Beth Howland
Beth Howland was an American actress best known for her role as the high-strung waitress Vera Louise Gorman on the long-running sitcom "Alice."
- 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_69d8b9f6d394819082a6d69fd1e23d2f |
completed | April 10, 2026, 8:51 a.m. |
| NER | Named-entity recognition | batch_69e4a30a11748190be41361d108aee58 |
completed | April 19, 2026, 9:40 a.m. |
Created at: April 10, 2026, 10:20 a.m.