Triple
T19305959
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Arlene Francis |
E482827
|
entity |
| Predicate | coStarredWith |
P14987
|
FINISHED |
| Object | Dorothy Kilgallen |
—
|
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: Dorothy Kilgallen | Statement: [Arlene Francis, coStarredWith, Dorothy Kilgallen]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Dorothy Kilgallen Context triple: [Arlene Francis, coStarredWith, Dorothy Kilgallen]
-
A.
Dorothy Kilgallen
chosen
Dorothy Kilgallen was an American journalist and television personality best known as a sharp-witted newspaper columnist and longtime panelist on the game show "What's My Line?".
-
B.
Martha Ludden
Martha Ludden is the daughter of American television personality and game show host Allen Ludden.
-
C.
Walda Winchell
Walda Winchell is the daughter of influential American newspaper and radio gossip columnist Walter Winchell.
-
D.
Marguerite Lauer
Marguerite Lauer was the wife of renowned French Egyptologist Jean-Philippe Lauer.
-
E.
Hildy Johnson
Hildy Johnson is the fast-talking, ambitious newspaper reporter at the center of the classic newsroom comedy "The Front Page."
- 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_69d8e8d04d5c8190baa816986f2b1d1e |
completed | April 10, 2026, 12:10 p.m. |
| NER | Named-entity recognition | batch_69e604c84fe08190869463bdd0324160 |
completed | April 20, 2026, 10:49 a.m. |
Created at: April 10, 2026, 1:31 p.m.