Triple
T17586458
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Michael Herr |
E428334
|
entity |
| Predicate | name |
P16
|
FINISHED |
| Object | Michael Herr |
—
|
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: Michael Herr | Statement: [Michael Herr, name, Michael Herr]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Michael Herr Context triple: [Michael Herr, name, Michael Herr]
-
A.
Michael Herr
chosen
Michael Herr was an American writer and war correspondent best known for his influential Vietnam War memoir "Dispatches" and his work on screenplays such as "Apocalypse Now" and "Full Metal Jacket."
-
B.
Mark Bowden
Mark Bowden is an American journalist and author best known for his nonfiction works on modern warfare and crime, including the acclaimed book "Black Hawk Down."
-
C.
Cornelius Ryan
Cornelius Ryan was an Irish-born journalist and historian best known for his meticulously researched World War II books, including the nonfiction work that inspired the film "A Bridge Too Far."
-
D.
Larry Konner
Larry Konner is a screenwriter best known for co-writing the film adaptation of the fantasy novel "Eragon."
-
E.
Tim O'Brien
Tim O'Brien is an American novelist best known for his Vietnam War–themed works, particularly the acclaimed book "The Things They Carried."
- 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_69d889e1030481909950e140c63255b9 |
completed | April 10, 2026, 5:25 a.m. |
| NER | Named-entity recognition | batch_69e463d22f908190ae0f1eeafbe54459 |
completed | April 19, 2026, 5:10 a.m. |
Created at: April 10, 2026, 5:50 a.m.