Triple
T10339215
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Frank Burns |
E243084
|
entity |
| Predicate | antagonisticTo |
P18963
|
FINISHED |
| Object | Radar O'Reilly |
E856923
|
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: Radar O'Reilly | Statement: [Frank Burns, antagonisticTo, Radar O'Reilly]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Radar O'Reilly Context triple: [Frank Burns, antagonisticTo, Radar O'Reilly]
-
A.
Radar O'Reilly
chosen
Radar O'Reilly is the naive yet resourceful company clerk from the TV series M*A*S*H, known for his uncanny ability to anticipate his commanding officer's needs.
-
B.
Don Roderick
Don Roderick is the legendary last Visigothic king of Spain, often depicted in literature as a tragic figure whose downfall heralds the Moorish conquest of the Iberian Peninsula.
-
C.
Ruppert
Ruppert is a masculine given name and surname of Germanic origin, related to the name Rupert.
-
D.
Roscoe Raider
Roscoe Raider is the costumed mascot representing the Milwaukee School of Engineering’s athletic teams and school spirit.
-
E.
Rick Wills
Rick Wills is an English rock bassist best known for his work with bands such as Foreigner, Small Faces, and Bad Company.
- 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_69d381af787481908bc401325c760a88 |
completed | April 6, 2026, 9:49 a.m. |
| NER | Named-entity recognition | batch_69d4e0a470948190959f298dd6110bf3 |
completed | April 7, 2026, 10:47 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d79508427c81909db511e969bc9ddb |
completed | April 9, 2026, 12:01 p.m. |
Created at: April 6, 2026, 11:54 a.m.