Triple
T11585900
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ohi Racecourse |
E274752
|
entity |
| Predicate | alsoKnownAs |
P39
|
FINISHED |
| Object | Tokyo City Keiba |
E934920
|
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: Tokyo City Keiba | Statement: [Ohi Racecourse, alsoKnownAs, Tokyo City Keiba]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Tokyo City Keiba Context triple: [Ohi Racecourse, alsoKnownAs, Tokyo City Keiba]
-
A.
Tokyo City Keiba
chosen
Tokyo City Keiba is the public operator of horse racing events and facilities in Tokyo, best known for managing the Ohi Racecourse and its popular night races.
-
B.
Tokyo Kyojin
Tokyo Kyojin is an alternate name for the Yomiuri Giants, one of Japan’s most historic and successful professional baseball teams based in Tokyo.
-
C.
Keiō
Keiō was the final Japanese era of the Edo period, spanning the turbulent years leading up to the Meiji Restoration.
-
D.
Takarazuka
Takarazuka is a Japanese city in Hyōgo Prefecture best known for the all-female Takarazuka Revue theater troupe and its popular hot spring resorts.
-
E.
Gaimushō
Gaimushō is Japan’s Ministry of Foreign Affairs, responsible for managing the country’s diplomatic relations and international policies.
- 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_69d6aae6b14c81908dc5a74bad7591f9 |
completed | April 8, 2026, 7:22 p.m. |
| NER | Named-entity recognition | batch_69d89462203881908870e991a5b21770 |
completed | April 10, 2026, 6:10 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ee86df14048190ae8f6d8b11610079 |
completed | April 26, 2026, 9:42 p.m. |
Created at: April 8, 2026, 9:38 p.m.