Triple
T32518190
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | ICANN accountability framework |
E831111
|
entity |
| Predicate | aimsToLimit |
P28788
|
FINISHED |
| Object | ICANN Board discretion through checks and balances |
—
|
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: ICANN Board discretion through checks and balances | Statement: [ICANN accountability framework, aimsToLimit, ICANN Board discretion through checks and balances]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: aimsToLimit Context triple: [ICANN accountability framework, aimsToLimit, ICANN Board discretion through checks and balances]
-
A.
aimedToLimit
chosen
Indicates an action or policy that was intentionally directed toward restricting, reducing, or constraining something.
-
B.
aimsToControl
Indicates an intention or effort by one entity to gain power over, direct, or regulate another entity or situation.
-
C.
limitaCon
Indicates that one entity imposes a restriction, constraint, or limit on another entity or its behavior.
-
D.
aimsToBalance
Indicates an intention or effort by one entity to bring multiple elements, forces, or conditions into a state of equilibrium.
-
E.
aimsToMeasure
Indicates that one entity is intended or designed to quantify, assess, or evaluate another entity or property.
- 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_69f34923e1548190be0524205d8cdf8f |
completed | April 30, 2026, 12:20 p.m. |
| NER | Named-entity recognition | batch_69f6c4b239ac8190835950194b69d649 |
completed | May 3, 2026, 3:44 a.m. |
| PD | Predicate disambiguation | batch_69f6bd2a14b081908162923dfbf0a6f4 |
completed | May 3, 2026, 3:12 a.m. |
Created at: May 1, 2026, 1 a.m.