Triple
T20117704
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Beggar on Horseback |
E490510
|
entity |
| Predicate | author |
P4
|
FINISHED |
| Object | Marc Connelly |
—
|
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: Marc Connelly | Statement: [Beggar on Horseback, author, Marc Connelly]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Marc Connelly Context triple: [Beggar on Horseback, author, Marc Connelly]
-
A.
Marc Connelly
chosen
Marc Connelly was an American playwright, director, and member of the Algonquin Round Table who won the Pulitzer Prize for Drama for "The Green Pastures."
-
B.
Ken Connell
Ken Connell is a Marvel Comics character who becomes the human wielder of the immensely powerful cosmic artifact known as the Star Brand.
-
C.
Greg Connell
Greg Connell was an Australian pilot best known as the longtime partner of entertainer Peter Allen, whose relationship is depicted in the musical "The Boy from Oz."
-
D.
Chris Connolly
Chris Connolly is a personal name shared by multiple individuals, including professionals in fields such as sports, media, and the arts.
-
E.
Mark Connolly
Mark Connolly is a notable individual distinguished enough to be recognized as a prominent bearer of the Connolly surname.
- 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_69da62636cc08190982cc71733a17b8d |
completed | April 11, 2026, 3:01 p.m. |
| NER | Named-entity recognition | batch_69e6673ab4e08190b76ec742605e103b |
completed | April 20, 2026, 5:49 p.m. |
Created at: April 11, 2026, 11:30 p.m.