Triple
T22050651
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Revenue (Topic 606) |
E544871
|
entity |
| Predicate | requiresJudgment |
P106530
|
FINISHED |
| Object | assessment of performance obligations |
—
|
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: assessment of performance obligations | Statement: [Revenue (Topic 606), requiresJudgment, assessment of performance obligations]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: requiresJudgment Context triple: [Revenue (Topic 606), requiresJudgment, assessment of performance obligations]
-
A.
requiresJudgeToBe
Indicates that a situation, action, or process necessitates the judge to possess or be in a specific state, role, or condition.
-
B.
requiresDecision
chosen
Indicates that a choice or judgment must be made regarding the associated entities or situation.
-
C.
requiresAssessmentOf
Indicates that one entity necessitates an evaluation, review, or judgment to be performed on another entity before proceeding or fulfilling a condition.
-
D.
requiresAssessmentBy
Indicates that one entity must be formally evaluated, reviewed, or judged by another specified entity before proceeding or being accepted.
-
E.
requiresJudgeImpartiality
Indicates that the situation or action necessitates a judge to remain unbiased and impartial in making decisions or evaluations.
- 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_69e11e32445c8190ab97089b48a130bb |
completed | April 16, 2026, 5:36 p.m. |
| NER | Named-entity recognition | batch_69f1283386f081908b70df81f38a5b1c |
completed | April 28, 2026, 9:35 p.m. |
| PD | Predicate disambiguation | batch_69e6f643ca74819083e8ab78e843f243 |
completed | April 21, 2026, 4 a.m. |
Created at: April 16, 2026, 8:26 p.m.