Triple
T20543008
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mir-NASA program |
E504393
|
entity |
| Predicate | sentAstronaut |
P122385
|
FINISHED |
| Object | Andrew Thomas |
—
|
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: Andrew Thomas | Statement: [Mir-NASA program, sentAstronaut, Andrew Thomas]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Andrew Thomas Context triple: [Mir-NASA program, sentAstronaut, Andrew Thomas]
-
A.
Andrew Thomas
chosen
Andrew Thomas is an Australian-born NASA astronaut and aerospace engineer who flew on multiple Space Shuttle missions, including long-duration stays on the Mir space station.
-
B.
John Thomas
John Thomas is an author known for writing about the Predator franchise.
-
C.
John Thomas
John Thomas is a creator best known for developing the character Mac Eliot.
-
D.
John Thomas
John Thomas is a film producer best known for his work on the action thriller "Executive Decision."
-
E.
John Thomas
John Thomas was a 19th-century British sculptor known for his architectural and commemorative works, including prominent public monuments.
- 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_69e0b4b476648190bc6019622ae54d3c |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e6a293feac8190b27848b64f2db1fe |
completed | April 20, 2026, 10:03 p.m. |
Created at: April 16, 2026, 11:38 a.m.