Triple
T17843856
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jayne Houdyshell |
E445603
|
entity |
| Predicate | hasRole |
P161
|
FINISHED |
| Object | Ann Kron in Well |
—
|
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: Ann Kron in Well | Statement: [Jayne Houdyshell, hasRole, Ann Kron in Well]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Ann Kron in Well Context triple: [Jayne Houdyshell, hasRole, Ann Kron in Well]
-
A.
Ann Kron
chosen
Ann Kron is a central character in the 2017 film "Well," around whom the story’s main events and emotional developments revolve.
-
B.
Emmy Hennings
Emmy Hennings was a German poet, performer, and writer who co-founded the Cabaret Voltaire in Zurich and became one of the central artistic and spiritual figures of the Dada movement.
-
C.
Joanna Kerns
Joanna Kerns is an American actress best known for playing the mother, Maggie Seaver, on the 1980s television sitcom "Growing Pains."
-
D.
Greta Kline
Greta Kline is an American indie rock musician and singer-songwriter best known as the frontwoman of the band Frankie Cosmos.
-
E.
Ari Wegner
Ari Wegner is an acclaimed Australian cinematographer known for her visually striking work on films such as "The Power of the Dog."
- 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_69d8b9f1a6d881909f024bc603111cdb |
completed | April 10, 2026, 8:50 a.m. |
| NER | Named-entity recognition | batch_69e48ff980048190b496c55b83b3b318 |
completed | April 19, 2026, 8:19 a.m. |
Created at: April 10, 2026, 10:16 a.m.