Triple
T37069643
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Aki Province |
E917538
|
entity |
| Predicate | hasHistoricRoad |
P12633
|
FINISHED |
| Object | Sanyōdō |
—
|
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: Sanyōdō | Statement: [Aki Province, hasHistoricRoad, Sanyōdō]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasHistoricRoad Context triple: [Aki Province, hasHistoricRoad, Sanyōdō]
-
A.
hasRoadHistory
Indicates that there exists a recorded history or sequence of past states, events, or changes associated with a particular road.
-
B.
hasHistoricStreet
Indicates that an entity is associated with or located on a street that has recognized historical significance.
-
C.
isHistoricStreet
Indicates that a street has recognized historical significance or heritage status.
-
D.
historicRoute
Indicates that a route has historical significance, typically due to its age, past usage, or role in notable events.
-
E.
hasHistoricalRoute
chosen
Indicates that an entity possesses or is associated with a route that has historical significance or origin.
- 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_69f76e9771e08190a690834e3cd20654 |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_69ff7bc112088190851501fb2a16103d |
completed | May 9, 2026, 6:24 p.m. |
| PD | Predicate disambiguation | batch_69ff7b45507c81909753866ad733601a |
completed | May 9, 2026, 6:21 p.m. |
Created at: May 3, 2026, 4:14 p.m.