Triple
T32424636
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 園城寺 |
E828544
|
entity |
| Predicate | hasAlternateReading |
P35086
|
FINISHED |
| Object | Onjō-ji |
—
|
NE NERFINISHED |
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: Onjō-ji | Statement: [園城寺, hasAlternateReading, Onjō-ji]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasAlternateReading Context triple: [園城寺, hasAlternateReading, Onjō-ji]
-
A.
hasVariantReadingsWith
Indicates a relationship where two textual items are linked because they exhibit differing or alternative readings of (typically) the same underlying content.
-
B.
hasAlternativeVocalization
chosen
Indicates that an entity has another valid way it can be vocalized or pronounced, distinct from its primary or standard vocalization.
-
C.
hasKanjiReading
Indicates that a written kanji character is associated with a specific reading or pronunciation.
-
D.
alternativeKanjiForm
Indicates that one kanji character or writing is an alternative form of another kanji for the same word or concept.
-
E.
hasMandarinReading
Indicates that an entity is associated with a specific reading or pronunciation in Mandarin Chinese.
- 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_69f3491b28bc8190b75cea7a507f337b |
completed | April 30, 2026, 12:20 p.m. |
| NER | Named-entity recognition | batch_69fcec5f8b448190b48330a19b462d24 |
completed | May 7, 2026, 7:47 p.m. |
| PD | Predicate disambiguation | batch_69fceaf1e23881908ca24160a638e329 |
completed | May 7, 2026, 7:41 p.m. |
Created at: May 1, 2026, 12:54 a.m.