Triple
T8276115
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Brandeis Brief |
E193550
|
entity |
| Predicate | approachCharacterizedAs |
P662
|
FINISHED |
| Object | fact-based advocacy |
—
|
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: fact-based advocacy | Statement: [Brandeis Brief, approachCharacterizedAs, fact-based advocacy]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: approachCharacterizedAs Context triple: [Brandeis Brief, approachCharacterizedAs, fact-based advocacy]
-
A.
characterizedBy
chosen
Indicates that one entity possesses a defining quality, feature, or attribute expressed by another entity.
-
B.
findingCharacterization
Indicates that a finding is being described or classified in terms of its nature, features, or diagnostic significance.
-
C.
ruleCharacterization
Indicates that one rule is described, defined, or characterized in terms of another rule or set of rules.
-
D.
scopeCharacterization
Indicates how the extent, boundaries, or coverage of something is defined, described, or qualified in relation to another entity or context.
-
E.
characterizationFocus
Indicates that the primary emphasis or concern of a characterization is directed toward a particular aspect, feature, or dimension of the subject.
- 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_69ca82e14ae481908ffdb822cd2192bc |
completed | March 30, 2026, 2:04 p.m. |
| NER | Named-entity recognition | batch_69cb798d69508190b581ad8a38730175 |
completed | March 31, 2026, 7:36 a.m. |
| PD | Predicate disambiguation | batch_69cb70a4525481909399d313a6247ace |
completed | March 31, 2026, 6:58 a.m. |
Created at: March 30, 2026, 5:51 p.m.