Triple
T2831709
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Rambo III |
E62251
|
entity |
| Predicate | character |
P662
|
FINISHED |
| Object | John Rambo |
E61455
|
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: John Rambo | Statement: [Rambo III, character, John Rambo]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: John Rambo Context triple: [Rambo III, character, John Rambo]
-
A.
John Rambo
chosen
John Rambo is a fictional Vietnam War veteran and highly skilled but troubled combat specialist who became iconic as the central character of the "Rambo" action film series.
-
B.
Henry Luttrell
Henry Luttrell was an Irish Jacobite officer who later defected to the Williamite side during the Williamite War in Ireland and became notorious for his controversial role and subsequent assassination.
-
C.
Tommy Atkins
Tommy Atkins is a widely grown commercial mango cultivar known for its attractive color, long shelf life, and firm, fibrous flesh.
-
D.
Marshal Will Kane
Marshal Will Kane is the principled, embattled lawman at the center of the classic Western film "High Noon," known for facing a deadly showdown alone when his town abandons him.
-
E.
Morgan Luttrell
Morgan Luttrell is a Republican U.S. Representative from Texas and former Navy SEAL who serves in Congress after a career in military and veterans’ advocacy.
- 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_69ab4c3c39188190955b9c49d98463d8 |
completed | March 6, 2026, 9:50 p.m. |
| NER | Named-entity recognition | batch_69abdebe95188190bf65fb4cd88e2ec5 |
completed | March 7, 2026, 8:15 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b055d3dbb8819094df5e6751dd96c4 |
completed | March 10, 2026, 5:33 p.m. |
Created at: March 6, 2026, 10:01 p.m.