Triple
T16656046
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Birdman of Alcatraz |
E404730
|
entity |
| Predicate | author |
P4
|
FINISHED |
| Object | Thomas E. Gaddis |
E404730
|
NE FINISHED |
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: Thomas E. Gaddis | Statement: [Birdman of Alcatraz, author, Thomas E. Gaddis]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Thomas E. Gaddis Context triple: [Birdman of Alcatraz, author, Thomas E. Gaddis]
-
A.
Thomas E. Gaddis
chosen
Thomas E. Gaddis was an American writer best known for his biographical works on prisoners, most notably the book that inspired the film "Birdman of Alcatraz."
-
B.
William R. Pogue
William R. Pogue was an American astronaut, U.S. Air Force pilot, and Skylab 4 crew member known for his long-duration spaceflight and contributions to space station operations.
-
C.
John W. Blum
John W. Blum is a screenwriter best known for his work on the comedy film "The Man from the Diners' Club."
-
D.
Christopher Nourse
Christopher Nourse is a British arts administrator and producer known for his leadership roles in major dance and performing arts organizations.
-
E.
Ben Herring
Ben Herring is a New Zealand rugby union coach and former flanker known for his coaching roles in Japan and with various professional clubs.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (3 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_69d8838b5fbc81908c6575c132b82e80 |
completed | April 10, 2026, 4:58 a.m. |
| NER | Named-entity recognition | batch_69e37bfa45d8819081bf8579a7160389 |
completed | April 18, 2026, 12:41 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0084c6bf8c81909b376875ae038e3f |
completed | May 10, 2026, 1:14 p.m. |
Created at: April 10, 2026, 5:18 a.m.