Triple
T16069369
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | King Kong Escapes |
E389817
|
entity |
| Predicate | starring |
P1507
|
FINISHED |
| Object | Mie Hama |
E519621
|
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: Mie Hama | Statement: [King Kong Escapes, starring, Mie Hama]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mie Hama Context triple: [King Kong Escapes, starring, Mie Hama]
-
A.
Mie Hama
chosen
Mie Hama is a Japanese actress best known internationally for her role as a Bond girl in the James Bond film "You Only Live Twice."
-
B.
Rika Muranaka
Rika Muranaka is a Japanese composer best known for her influential music contributions to the Metal Gear Solid video game series.
-
C.
Kasumi Oga
Kasumi Oga is a Japanese composer best known for creating the music for the anime series "Gankutsuou: The Count of Monte Cristo."
-
D.
Minako Hamano
Minako Hamano is a Japanese video game composer best known for her work on major Nintendo franchises, including contributions to the music of Donkey Kong Country Returns and several Metroid titles.
-
E.
Maki Horikita
Maki Horikita is a Japanese actress known for her leading roles in popular television dramas and films during the 2000s and early 2010s.
- 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_69d86daf32ec8190a8c0466c8f49c3c0 |
completed | April 10, 2026, 3:25 a.m. |
| NER | Named-entity recognition | batch_69e183bb98c88190ae4b5773358078be |
completed | April 17, 2026, 12:50 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a003546d3e081908f1244b7f4fb1067 |
completed | May 10, 2026, 7:35 a.m. |
Created at: April 10, 2026, 4:57 a.m.