Triple
T34814526
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 秀司 |
E1003592
|
entity |
| Predicate | hasReadingSystem |
P205564
|
FINISHED |
| Object | Hepburn romanization |
E208003
|
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: Hepburn romanization | Statement: [秀司, hasReadingSystem, Hepburn romanization]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasReadingSystem Context triple: [秀司, hasReadingSystem, Hepburn romanization]
-
A.
readingSystem
Indicates a system or device that presents, interprets, or processes written or digital content for a user.
-
B.
hasReadingEnvironment
Indicates that an entity is associated with or situated in a particular environment or context in which reading takes place.
-
C.
hasReadingType
Indicates that an entity is associated with a specific category or mode of reading, such as a particular interpretation, format, or type of reading measurement.
-
D.
containsReading
Indicates that one entity includes or encompasses a particular reading (such as a measurement, value, or interpretation) within it.
-
E.
hasReading
Indicates that an entity is associated with a particular reading, such as a measured value, interpretation, or recorded observation.
- F. None of above. chosen
Provenance (5 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_69f76db600b88190989abdf08fce3b27 |
completed | May 3, 2026, 3:45 p.m. |
| NER | Named-entity recognition | batch_6a037c92f03c8190ae2751270b195423 |
completed | May 12, 2026, 7:16 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a376fb5819c8190999fac08e77483de |
completed | June 21, 2026, 4:59 a.m. |
| PD | Predicate disambiguation | batch_6a0379fd7aac8190873077e63873aa72 |
completed | May 12, 2026, 7:05 p.m. |
| PDg | Predicate description generation | batch_6a037c80ba448190853011097a151b7e |
completed | May 12, 2026, 7:16 p.m. |
Created at: May 3, 2026, 3:59 p.m.