Triple
T9888228
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Iki |
E181389
|
entity |
| Predicate | contrastsWith |
P278
|
FINISHED |
| Object | Miyabi |
E231912
|
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: Miyabi | Statement: [Iki, contrastsWith, Miyabi]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Miyabi Context triple: [Iki, contrastsWith, Miyabi]
-
A.
Miyabi
chosen
Miyabi is a traditional Japanese-inspired lighting theme used on Tokyo Skytree, characterized by elegant, refined color schemes that evoke classical aesthetics.
-
B.
Miyazu
Miyazu is a coastal city in northern Kyoto Prefecture, Japan, best known as the gateway to the scenic sandbar Amanohashidate, one of Japan’s traditional “Three Views.”
-
C.
Miya
Miya is a Japanese honorific suffix historically used in imperial and aristocratic titles, particularly within branches of the Japanese Imperial Family such as the Higashikuni-no-miya.
-
D.
Miya
Miya is a Chadic language spoken in parts of northern Nigeria, known for its complex tonal system and Afroasiatic linguistic roots.
-
E.
Miho
Miho is a deadly, silent assassin and protector of Old Town in Frank Miller's Sin City graphic novel series.
- 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_69ca8283a6708190801af7a25a7ebb9f |
completed | March 30, 2026, 2:02 p.m. |
| NER | Named-entity recognition | batch_69cdb4592db881909b134834dde614d8 |
completed | April 2, 2026, 12:12 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d8dbe24a64819098bc94a8a62cc46b |
completed | April 10, 2026, 11:15 a.m. |
Created at: March 30, 2026, 8:39 p.m.