Triple
T20882015
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Madigan |
E514174
|
entity |
| Predicate | starring |
P1507
|
FINISHED |
| Object | Inger Stevens |
—
|
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: Inger Stevens | Statement: [Madigan, starring, Inger Stevens]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Inger Stevens Context triple: [Madigan, starring, Inger Stevens]
-
A.
Inger Stevens
chosen
Inger Stevens was a Swedish-American actress best known for her roles in 1950s and 1960s films and television, often portraying complex, emotionally nuanced characters.
-
B.
Louise Erickson
Louise Erickson is an American actress best known for her work in mid-20th-century radio and film, and for having been married to actor Ben Gazzara.
-
C.
Barbara Sturgeon
Barbara Sturgeon is a British radio broadcaster and presenter known for her long career with BBC local radio.
-
D.
Ina Fagan
Ina Fagan, better known by her stage name Ina Claire, was a prominent American stage and film actress of the early 20th century renowned for her sophisticated comedic roles.
-
E.
Carol Stevens
Carol Stevens is best known as one of the former wives of American novelist and journalist Norman Mailer.
- 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_69e0b4f733f081908a401c0b7beb0b9f |
completed | April 16, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69e6c67a33548190b0f5ba58b001d387 |
completed | April 21, 2026, 12:36 a.m. |
Created at: April 16, 2026, 12:46 p.m.