Triple
T11791803
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | STS-108 |
E280404
|
entity |
| Predicate | pilot |
P2087
|
FINISHED |
| Object | Mark E. Kelly |
E768275
|
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: Mark E. Kelly | Statement: [STS-108, pilot, Mark E. Kelly]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mark E. Kelly Context triple: [STS-108, pilot, Mark E. Kelly]
-
A.
Mark E. Kelly
chosen
Mark E. Kelly is a retired NASA astronaut and U.S. Navy captain who later became a United States Senator from Arizona.
-
B.
Navin R. Johnson
Navin R. Johnson is the naive, bumbling protagonist of the 1979 comedy film "The Jerk," famously portrayed by Steve Martin.
-
C.
Michael S. Turner
Michael S. Turner is an American cosmologist and astrophysicist known for pioneering work on dark energy, inflation, and the early universe.
-
D.
Jay Ashcroft
Jay Ashcroft is a Missouri politician and attorney who has served as the state's Secretary of State and is the son of former U.S. Attorney General John Ashcroft.
-
E.
James M. Cox
James M. Cox was an American newspaper publisher, media entrepreneur, and Democratic politician who served as governor of Ohio and was the 1920 Democratic nominee for U.S. president.
- 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_69d6ab258b808190b1735835c841e3a4 |
completed | April 8, 2026, 7:23 p.m. |
| NER | Named-entity recognition | batch_69d8a588d2c881909783c2d678c2a474 |
completed | April 10, 2026, 7:23 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f09107fd2481908d765d2188035012 |
completed | April 28, 2026, 10:50 a.m. |
Created at: April 8, 2026, 9:42 p.m.