Triple
T9577732
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | James N. Mattis |
E231086
|
entity |
| Predicate | nickname |
P55
|
FINISHED |
| Object | Mad Dog |
E763776
|
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: Mad Dog | Statement: [James N. Mattis, nickname, Mad Dog]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mad Dog Context triple: [James N. Mattis, nickname, Mad Dog]
-
A.
Mad Dog
chosen
Mad Dog is the vicious outlaw gunslinger and primary antagonist in the 1885 segment of the film "Back to the Future Part III."
-
B.
Mad Dogs
Mad Dogs is a British dark comedy-drama television series about a group of middle-aged friends whose holiday in Spain spirals into crime and chaos.
-
C.
Black Dogs
"Black Dogs" is a 1992 novel by Ian McEwan that explores the aftermath of World War II and the clash between rationalism and spiritual belief through the story of a troubled marriage.
-
D.
White Dog
White Dog is a crime novel in the Jack Irish series by Australian author Peter Temple, featuring the Melbourne lawyer and debt-collector embroiled in a complex investigation.
-
E.
White Dog
White Dog is a 1982 American drama-horror film directed by Samuel Fuller that explores racism through the story of a dog trained to attack Black people.
- 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_69ca848091c48190bc313d6620d09555 |
completed | March 30, 2026, 2:11 p.m. |
| NER | Named-entity recognition | batch_69cd99ad7d108190a0b8c975351ea727 |
completed | April 1, 2026, 10:18 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d16155b3288190ac135c3a1e58cc7e |
completed | April 4, 2026, 7:07 p.m. |
Created at: March 30, 2026, 8:05 p.m.