Triple
T9489719
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Balaam’s oracles |
E228853
|
entity |
| Predicate | foundInChapters |
P36548
|
FINISHED |
| Object | Numbers 22–24 |
—
|
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: Numbers 22–24 | Statement: [Balaam’s oracles, foundInChapters, Numbers 22–24]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: foundInChapters Context triple: [Balaam’s oracles, foundInChapters, Numbers 22–24]
-
A.
foundInChapter
chosen
Indicates that something (such as a concept, section, or element) is contained within or occurs in a specific chapter.
-
B.
containsChapter
Indicates that one entity (typically a larger work or document) includes another entity as a chapter within its structure.
-
C.
chapterOn
Indicates that one entity (typically a chapter) is about, discusses, or focuses on the subject represented by another entity.
-
D.
primarySourceChapters
Indicates that specific chapters are identified as the primary source material for the referenced content or work.
-
E.
foundInVolume
Indicates that one entity is physically or logically contained within, or occurs in, a specific volume (such as a book volume, data volume, or bounded collection).
- 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_69ca847424f081908180305555139f7a |
completed | March 30, 2026, 2:11 p.m. |
| NER | Named-entity recognition | batch_69cd80c6f6bc8190aa09422508bd5d23 |
completed | April 1, 2026, 8:32 p.m. |
| PD | Predicate disambiguation | batch_69cca561e6b0819090aa795f3c3a2083 |
completed | April 1, 2026, 4:56 a.m. |
Created at: March 30, 2026, 7:55 p.m.