Triple
T9940963
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Masayuki |
E194078
|
entity |
| Predicate | typicalWritingDirection |
P2264
|
FINISHED |
| Object | left-to-right in Latin script |
—
|
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: left-to-right in Latin script | Statement: [Masayuki, typicalWritingDirection, left-to-right in Latin script]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typicalWritingDirection Context triple: [Masayuki, typicalWritingDirection, left-to-right in Latin script]
-
A.
hasWritingDirection
chosen
Indicates the direction in which writing or text is read or written for a given script, language, or text system.
-
B.
translationDirection
Indicates the source and target languages involved in a translation, specifying the direction from the original language to the translated language.
-
C.
typicalLanguageOfReadings
Indicates the language that is most commonly used for readings or interpretations associated with a given entity.
-
D.
currentlyWrittenIn
Indicates that a work or document is, at the present time, expressed or composed in a particular language or writing system.
-
E.
languageOfWritings
Indicates that a specified language is the one in which certain writings or written works are composed.
- 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_69ca82e409348190a393777356b80a2a |
completed | March 30, 2026, 2:04 p.m. |
| NER | Named-entity recognition | batch_69cdb60f4ffc8190bfe916bb4a7bf5c5 |
completed | April 2, 2026, 12:19 a.m. |
| PD | Predicate disambiguation | batch_69cd1d9428cc81909b4b4938566d78a7 |
completed | April 1, 2026, 1:28 p.m. |
Created at: March 30, 2026, 8:44 p.m.