Triple
T22565090
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | D33 |
E557925
|
entity |
| Predicate | hasHunebedNumber |
P148752
|
FINISHED |
| Object | D33 |
—
|
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: D33 | Statement: [D33, hasHunebedNumber, D33]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasHunebedNumber Context triple: [D33, hasHunebedNumber, D33]
-
A.
hasHonden
Indicates that an entity possesses or includes a honden, typically referring to the main sanctuary building in a Shinto shrine.
-
B.
hasPilgrimageNumber
Indicates that an entity is associated with a specific pilgrimage identification number, typically used to track or distinguish individual pilgrimages or pilgrims.
-
C.
hasGateNumber
Indicates that an entity (such as a flight or departure) is associated with a specific gate number.
-
D.
hasHaiden
Indicates that something possesses or includes a haiden, typically a worship or prayer hall associated with a shrine.
-
E.
hasHellyNumber
Indicates that there exists a smallest integer h such that, for this family of sets, any subfamily in which every h sets have a nonempty intersection must itself have a nonempty overall intersection.
- F. None of above. chosen
Provenance (4 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_69e11e5ae4ac8190b1f503457603d969 |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f15fa8d8388190856198547d56dce6 |
completed | April 29, 2026, 1:32 a.m. |
| PD | Predicate disambiguation | batch_69ee626e6bb08190ada4dd8b48cc0c43 |
completed | April 26, 2026, 7:07 p.m. |
| PDg | Predicate description generation | batch_69ee8841e9cc81908d23b34215e3be71 |
completed | April 26, 2026, 9:48 p.m. |
Created at: April 16, 2026, 8:52 p.m.