Triple
T38580686
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hatsu-uma |
E932235
|
entity |
| Predicate | mainRitualActivity |
P65752
|
FINISHED |
| Object | shrine visits |
—
|
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: shrine visits | Statement: [Hatsu-uma, mainRitualActivity, shrine visits]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: mainRitualActivity Context triple: [Hatsu-uma, mainRitualActivity, shrine visits]
-
A.
ritualActivities
chosen
Indicates that one entity engages in, performs, or is associated with ritualistic or ceremonial activities in relation to another entity or context.
-
B.
ritualsDirectedAt
Indicates that certain rituals are performed with a specific entity, object, or target as their intended focus or recipient.
-
C.
ritualEvent
Indicates that an event is a ritual or ceremonial occurrence, typically involving prescribed actions, symbols, or practices performed according to tradition or custom.
-
D.
mainRitualTime
Indicates the time at which the primary or central ritual is performed.
-
E.
initiatesRitual
Indicates that one entity begins or sets in motion a ritual involving one or more other entities.
- 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_69f76ec654d48190b421111cf26e54d9 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_69fcdaa36f90819093f8661969990c7d |
completed | May 7, 2026, 6:32 p.m. |
| PD | Predicate disambiguation | batch_69fcd8fefc588190b063d7ea1ec87b07 |
completed | May 7, 2026, 6:25 p.m. |
Created at: May 3, 2026, 4:32 p.m.