Triple
T20287914
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | John Froines |
E509937
|
entity |
| Predicate | coDefendantWith |
P31780
|
FINISHED |
| Object | David Dellinger |
—
|
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: David Dellinger | Statement: [John Froines, coDefendantWith, David Dellinger]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: David Dellinger Context triple: [John Froines, coDefendantWith, David Dellinger]
-
A.
David Dellinger
chosen
David Dellinger was a prominent American pacifist and anti–Vietnam War activist best known as one of the Chicago Seven defendants.
-
B.
Tom Hayden
Tom Hayden was a prominent American social and political activist, author, and politician best known as a leader of the 1960s New Left and a key figure in the anti–Vietnam War and civil rights movements.
-
C.
David Boggs
David Boggs was an American electrical engineer and computer scientist best known as the co-inventor of Ethernet networking technology at Xerox PARC.
-
D.
Guy Carawan
Guy Carawan was an American folk musician and musicologist best known for popularizing the civil rights anthem "We Shall Overcome."
-
E.
Steven Reuther
Steven Reuther was an American film producer known for his work on major Hollywood movies such as "Pretty Woman" and other commercially successful dramas and thrillers.
- 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_69e0b4c652388190b782cad965e5a098 |
completed | April 16, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69e6769414488190b38e07fd1e989aba |
completed | April 20, 2026, 6:55 p.m. |
Created at: April 16, 2026, 11:09 a.m.