Triple
T28327832
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tianguan |
E717458
|
entity |
| Predicate | requestRitual |
P149215
|
FINISHED |
| Object | prayers for good fortune |
—
|
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: prayers for good fortune | Statement: [Tianguan, requestRitual, prayers for good fortune]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: requestRitual Context triple: [Tianguan, requestRitual, prayers for good fortune]
-
A.
initiatesRitual
Indicates that one entity begins or sets in motion a ritual involving one or more other entities.
-
B.
hasRitual
Indicates that an entity performs, observes, or is associated with a specific ritual or ceremonial practice.
-
C.
appearsInRitual
Indicates that an entity is included, featured, or participates as a component or element within a specific ritual.
-
D.
hasRituals
Indicates that one entity performs, observes, or is associated with specific rituals in relation to another entity or context.
-
E.
ritualsDirectedAt
chosen
Indicates that certain rituals are performed with a specific entity, object, or target as their intended focus or recipient.
- 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_69eff6e9a57c8190a69c2c74b5d72119 |
completed | April 27, 2026, 11:53 p.m. |
| NER | Named-entity recognition | batch_69f6562fd3488190be1acd8c526a28d2 |
completed | May 2, 2026, 7:53 p.m. |
| PD | Predicate disambiguation | batch_69f651a931748190a637e631a52bbfaa |
completed | May 2, 2026, 7:34 p.m. |
Created at: April 28, 2026, 12:29 a.m.