Triple
T7274266
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Geertje Dircx |
E162983
|
entity |
| Predicate | relativeCertaintyOfModelAttribution |
P36359
|
FINISHED |
| Object | disputed |
—
|
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: disputed | Statement: [Geertje Dircx, relativeCertaintyOfModelAttribution, disputed]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: relativeCertaintyOfModelAttribution Context triple: [Geertje Dircx, relativeCertaintyOfModelAttribution, disputed]
-
A.
hasCertainty
chosen
Indicates that a statement, belief, or relationship is associated with a specific level or degree of confidence or surety.
-
B.
requiresConfidenceOf
Indicates that one entity can only proceed, function, or be accepted if it has sufficient trust, assurance, or belief in the reliability or correctness of another entity.
-
C.
hasUncertainty
Indicates that the relationship or value is associated with some level or type of uncertainty rather than being fully definite or precise.
-
D.
trustModel
Indicates that one entity relies on or has confidence in the reliability, integrity, or performance of another entity or system.
-
E.
estimatedStrength
Indicates that a value represents an approximate or inferred level, magnitude, or intensity of something rather than a precisely measured strength.
- 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_69c6885c5964819085b209701769877f |
completed | March 27, 2026, 1:38 p.m. |
| NER | Named-entity recognition | batch_69c6eb8a0b4881908ff27c5a75bd4a95 |
completed | March 27, 2026, 8:41 p.m. |
| PD | Predicate disambiguation | batch_69c6e76a84a081908d4184c55b728e48 |
completed | March 27, 2026, 8:24 p.m. |
Created at: March 27, 2026, 2:58 p.m.