Triple
T17831893
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Gamera vs. Jiger |
E445276
|
entity |
| Predicate | setIn |
P1393
|
FINISHED |
| Object | Expo '70 |
—
|
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: Expo '70 | Statement: [Gamera vs. Jiger, setIn, Expo '70]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Expo '70 Context triple: [Gamera vs. Jiger, setIn, Expo '70]
-
A.
Expo ’70
chosen
Expo ’70 was the world’s fair held in Osaka, Japan, in 1970, renowned for its futuristic architecture, technological exhibits, and the iconic Tower of the Sun.
-
B.
Expo ’90
Expo ’90 was the 1990 World Exposition on horticulture and environmental harmony held in Osaka, Japan, showcasing global garden design and ecological themes.
-
C.
Expo 1964
Expo 1964 was a world's fair held in Switzerland that showcased technological progress, culture, and national identity during the mid-20th century.
-
D.
Expo '85 Tsukuba
Expo '85 Tsukuba was the 1985 World's Fair held in Tsukuba, Japan, showcasing cutting-edge science and technology exhibits from around the globe.
-
E.
Yokohama Expo 1989
Yokohama Expo 1989 was a world exposition held in Yokohama, Japan, showcasing futuristic urban culture, technology, and waterfront development.
- 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_69d8b9f1a6d881909f024bc603111cdb |
completed | April 10, 2026, 8:50 a.m. |
| NER | Named-entity recognition | batch_69e48d248ecc8190b3f0d001b539d960 |
completed | April 19, 2026, 8:07 a.m. |
Created at: April 10, 2026, 10:15 a.m.