Triple
T21607844
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kong family |
E533223
|
entity |
| Predicate | familyName |
P18
|
FINISHED |
| Object | Kong |
—
|
NE NERFINISHED |
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: Kong | Statement: [Kong family, familyName, Kong]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Kong Context triple: [Kong family, familyName, Kong]
-
A.
Kong
Kong is an inverted steel roller coaster at Six Flags Discovery Kingdom known for its multiple inversions and intense, suspended ride experience.
-
B.
Kong
chosen
Kong is a Chinese surname most famously associated with the philosopher Confucius and his descendants.
-
C.
Kong (MonsterVerse)
Kong (MonsterVerse) is a colossal, intelligent ape-like Titan who serves as one of the central heroic monsters in Legendary Pictures’ MonsterVerse franchise.
-
D.
KONG
KONG is a television station in the Seattle–Tacoma market, commonly associated with KING-TV as its sister station.
-
E.
Major T. J. "King" Kong
Major T. J. "King" Kong is a gung-ho U.S. Air Force bomber pilot in the satirical Cold War film "Dr. Strangelove," best known for his iconic scene riding a falling nuclear bomb like a rodeo cowboy.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e0c46411108190bba0d4176dffc9f3 |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69ef17e6378881908678dc903b8ba6ac |
completed | April 27, 2026, 8:01 a.m. |
Created at: April 16, 2026, 6:33 p.m.