Triple
T15856287
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Shiodome |
E384463
|
entity |
| Predicate | hasJapaneseName |
P9882
|
FINISHED |
| Object | 汐留 |
E1090671
|
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: 汐留 | Statement: [Shiodome, hasJapaneseName, 汐留]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: 汐留 Context triple: [Shiodome, hasJapaneseName, 汐留]
-
A.
汐留
chosen
汐留 is a modern waterfront district in Tokyo known for its high-rise office towers, media headquarters, shopping complexes, and proximity to Shiodome Shiosite and Hamarikyu Gardens.
-
B.
二子玉川
二子玉川 is a riverside commercial and residential district in Tokyo known for its large shopping complexes, stylish cafes, and family-friendly urban development along the Tama River.
-
C.
高輪
高輪 is a district in Minato, Tokyo, known for its mix of historic temples, residential areas, and proximity to major transport hubs like Shinagawa.
-
D.
神保町
神保町 is a Tokyo neighborhood famed as Japan’s largest used-book district, lined with countless bookstores, publishers, and cozy cafés.
-
E.
根津
根津は東京都文京区に位置し、古い町並みと根津神社で知られる歴史ある下町エリアです。
- 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_69d86da422088190aac39e32e6c68429 |
completed | April 10, 2026, 3:25 a.m. |
| NER | Named-entity recognition | batch_69e14cb08bd081908af2120eb2925441 |
completed | April 16, 2026, 8:55 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ffa14c1e508190a182db216cc4e326 |
completed | May 9, 2026, 9:04 p.m. |
Created at: April 10, 2026, 4:50 a.m.