Triple
T7593099
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hepburn |
E179787
|
entity |
| Predicate | usesMacronFor |
P2270
|
FINISHED |
| Object | long vowels such as ō and ū |
—
|
LITERAL 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: long vowels such as ō and ū | Statement: [Hepburn, usesMacronFor, long vowels such as ō and ū]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: usesMacronFor Context triple: [Hepburn, usesMacronFor, long vowels such as ō and ū]
-
A.
usesPrimaryFrenchGateway
Indicates that an entity routes its primary communications or connections through a main gateway located in or associated with French infrastructure or networks.
-
B.
usesDiacritics
chosen
Indicates that the referenced text or linguistic element employs diacritical marks as part of its written form.
-
C.
usesWord
Indicates that one entity employs, contains, or makes use of a particular word in its expression, content, or communication.
-
D.
usesForm
Indicates that one entity employs, applies, or operates through a particular form, format, or structured representation of something.
-
E.
hasAccent
Indicates that an entity speaks with or possesses a particular accent or distinctive pronunciation style.
- F. None of above.
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_69c69f3487ec8190bf7acdf2dd91e6d6 |
completed | March 27, 2026, 3:16 p.m. |
| NER | Named-entity recognition | batch_69c6f9b92c348190b547f0aacfb8d6be |
completed | March 27, 2026, 9:42 p.m. |
| PD | Predicate disambiguation | batch_69c6f4e2e42c8190afc802c4796c9cc2 |
completed | March 27, 2026, 9:21 p.m. |
Created at: March 27, 2026, 3:53 p.m.