Triple
T28834929
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jacob's Well |
E728151
|
entity |
| Predicate | gospelChapter |
P165649
|
FINISHED |
| Object | John 4 |
—
|
NE NERFINISHED |
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: John 4 | Statement: [Jacob's Well, gospelChapter, John 4]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: gospelChapter Context triple: [Jacob's Well, gospelChapter, John 4]
-
A.
chapterAndVerse
Indicates a relationship where a specific chapter is associated with a specific verse (or set of verses) within a structured text, such as a book or document.
-
B.
gospelEpisode
Indicates that one entity is an episode or segment within a gospel narrative or gospel-related series associated with another entity.
-
C.
scripturalChapters
Indicates that one entity is composed of, contains, or is divided into the specified scriptural chapters.
-
D.
gospelReadingFrom
Indicates that a particular gospel reading is taken from or sourced in a specified scriptural passage or book.
-
E.
scripturalSection
Indicates a relationship where one text or passage is a specific section or subdivision within a larger scriptural work.
- F. None of above. chosen
Provenance (4 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_69f0319dc6088190bbfaa206d40ed74a |
completed | April 28, 2026, 4:03 a.m. |
| NER | Named-entity recognition | batch_69f6596cb08c8190908072a531179743 |
completed | May 2, 2026, 8:07 p.m. |
| PD | Predicate disambiguation | batch_69f65762b5e481908a30ca963dcba4be |
completed | May 2, 2026, 7:58 p.m. |
| PDg | Predicate description generation | batch_69f658ebeca4819096beb3f98f73fe31 |
completed | May 2, 2026, 8:05 p.m. |
Created at: April 28, 2026, 6:39 a.m.