Triple
T14770700
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Steven Conrad |
E347123
|
entity |
| Predicate | created |
P538
|
FINISHED |
| Object | Patriot |
E738693
|
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: Patriot | Statement: [Steven Conrad, created, Patriot]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Patriot Context triple: [Steven Conrad, created, Patriot]
-
A.
Patriot
Patriot is the nickname for the VH-92A, a U.S. Marine Corps variant of the Sikorsky S-92 helicopter used for presidential transport.
-
B.
Patriot
Patriot is a U.S.-designed, long-range, surface-to-air missile defense system widely used by allied nations to intercept aircraft, cruise missiles, and ballistic missiles.
-
C.
Patriot
chosen
Patriot is a darkly comedic espionage television series following an intelligence officer whose undercover job at a Midwestern industrial piping firm complicates his already precarious mental state.
-
D.
Patriot
Patriot is a steel floorless roller coaster at California’s Great America known for its inversions and smooth, looping layout.
-
E.
Patriot
Patriot is a character from the children's game Cooties, typically depicted as a playful, patriotic-themed figure within the game's imaginative cast.
- 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_69d822e8896c819091169882f9b20486 |
completed | April 9, 2026, 10:06 p.m. |
| NER | Named-entity recognition | batch_69dec81334e08190a77d760e507d00ed |
completed | April 14, 2026, 11:04 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fe24b41df881908119e183b8299c48 |
completed | May 8, 2026, 6 p.m. |
Created at: April 10, 2026, 1:31 a.m.