Triple
T9220406
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | al-Mustasfa |
E221344
|
entity |
| Predicate | epistemologicalConcern |
P80926
|
FINISHED |
| Object | certainty and probability in legal reasoning |
—
|
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: certainty and probability in legal reasoning | Statement: [al-Mustasfa, epistemologicalConcern, certainty and probability in legal reasoning]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: epistemologicalConcern Context triple: [al-Mustasfa, epistemologicalConcern, certainty and probability in legal reasoning]
-
A.
epistemologicalFocus
chosen
Indicates that something is primarily concerned with questions about knowledge, its nature, sources, justification, or limits.
-
B.
epistemicAttitude
Indicates the type or stance of a subject’s knowledge, belief, or certainty toward a proposition or statement.
-
C.
epistemicStatus
Indicates the degree of certainty, justification, or knowledge an agent has regarding a particular proposition or claim.
-
D.
epistemicRole
Indicates the role an entity plays in a knowledge-related context, such as being a knower, source, or bearer of information or belief.
-
E.
epistemicPriority
Indicates that one piece of information, belief, or source is treated as more authoritative or reliable than another in determining what is accepted as true.
- 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_69ca83eae42c8190a0ea9e040710a277 |
completed | March 30, 2026, 2:08 p.m. |
| NER | Named-entity recognition | batch_69ccda74808081908d4bf890759e7120 |
completed | April 1, 2026, 8:42 a.m. |
| PD | Predicate disambiguation | batch_69cc7a3daeb481908b0abde3fbc1f1f0 |
completed | April 1, 2026, 1:51 a.m. |
Created at: March 30, 2026, 7:28 p.m.