Triple
T37648357
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Season after Pentecost |
E937101
|
entity |
| Predicate | countedBy |
P55908
|
FINISHED |
| Object | numbered Sundays after Pentecost |
—
|
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: numbered Sundays after Pentecost | Statement: [Season after Pentecost, countedBy, numbered Sundays after Pentecost]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: countedBy Context triple: [Season after Pentecost, countedBy, numbered Sundays after Pentecost]
-
A.
areCountedBy
chosen
Indicates that one entity serves as the counting mechanism, record, or process by which the quantity of another entity is determined.
-
B.
count
Indicates the numerical quantity or total number of instances of a specified entity or event.
-
C.
numberOfCounts
Indicates the total quantity or tally of discrete occurrences, items, or instances associated with an entity or event.
-
D.
givesCountAs
Indicates that one entity’s act of giving is treated or recognized as equivalent to another specified giving action or contribution.
-
E.
isCountedAs
Indicates that one entity is treated or included as part of the tally, total, or quantitative assessment of another entity.
- 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_69f76ed4fe908190b8061c5c135e0971 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_6a037c8efcd4819088c2aeead65d93df |
completed | May 12, 2026, 7:16 p.m. |
| PD | Predicate disambiguation | batch_6a037a1553e08190bb7424c448cb1f33 |
completed | May 12, 2026, 7:05 p.m. |
Created at: May 3, 2026, 4:18 p.m.