Triple
T1000760
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Seven Bowls |
E21596
|
entity |
| Predicate | prefiguredBy |
P20431
|
FINISHED |
| Object | Seven Trumpets |
—
|
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: Seven Trumpets | Statement: [Seven Bowls, prefiguredBy, Seven Trumpets]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: prefiguredBy Context triple: [Seven Bowls, prefiguredBy, Seven Trumpets]
-
A.
preludeTo
chosen
Indicates that one event, action, or state occurs earlier and serves as an introduction or lead-in to another.
-
B.
precondition
Indicates that one event, state, or condition must be true or occur before another event, state, or condition can validly or successfully take place.
-
C.
precedentFor
Indicates that one situation, decision, or case serves as an authoritative example or basis for deciding or interpreting another.
-
D.
defined
Indicates that one entity specifies, explains, or establishes the meaning, scope, or identity of another entity.
-
E.
predecessor
Indicates that one entity comes before another in an ordered sequence or succession.
- 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_69a493c476b48190b41fc5e793171cc6 |
completed | March 1, 2026, 7:30 p.m. |
| NER | Named-entity recognition | batch_69a4b4fb18b88190ae2d620aaaff4f90 |
completed | March 1, 2026, 9:51 p.m. |
| PD | Predicate disambiguation | batch_69a4b2b057c48190b9e42df9246b3757 |
completed | March 1, 2026, 9:42 p.m. |
Created at: March 1, 2026, 7:41 p.m.