Triple
T3942875
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tower of Silence |
E92075
|
entity |
| Predicate | ritualContext |
P36127
|
FINISHED |
| Object | Zoroastrian funerary rites |
—
|
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: Zoroastrian funerary rites | Statement: [Tower of Silence, ritualContext, Zoroastrian funerary rites]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: ritualContext Context triple: [Tower of Silence, ritualContext, Zoroastrian funerary rites]
-
A.
hasRitualContext
chosen
Indicates that one entity is associated with, or occurs within, a ritual or ceremonial context in relation to another entity.
-
B.
ritualCharacteristics
Indicates the defining features, practices, or attributes that characterize a particular ritual.
-
C.
ritualStructure
Indicates a relationship where an entity is a structure or built feature specifically used for performing rituals or ceremonial practices.
-
D.
ritualPurpose
Indicates the intended function, goal, or role that a ritual is meant to serve or fulfill.
-
E.
partOfRitual
Indicates that an action, object, or event is included as a component or step within a larger ritual.
- 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_69aed965502c8190904ebad1203a4ae8 |
completed | March 9, 2026, 2:29 p.m. |
| NER | Named-entity recognition | batch_69aef1515c688190a38332aedeed8a76 |
completed | March 9, 2026, 4:12 p.m. |
| PD | Predicate disambiguation | batch_69aee764235081909309b3c982f322a9 |
completed | March 9, 2026, 3:29 p.m. |
Created at: March 9, 2026, 3:24 p.m.