Triple
T27663155
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | CAA |
E697169
|
entity |
| Predicate | tagPurpose |
P163517
|
FINISHED |
| Object | iodef: specify contact or reporting URI for policy violations |
—
|
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: iodef: specify contact or reporting URI for policy violations | Statement: [CAA, tagPurpose, iodef: specify contact or reporting URI for policy violations]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: tagPurpose Context triple: [CAA, tagPurpose, iodef: specify contact or reporting URI for policy violations]
-
A.
purpose
Indicates that one entity exists, is done, or is used in order to achieve, support, or serve the goal, function, or intended outcome of another entity.
-
B.
notationPurpose
Indicates that one notation is used with the specific purpose or function of representing, explaining, or supporting another entity or concept.
-
C.
traditionalPurpose
Indicates that something serves a role, function, or use that is established by long-standing custom or tradition.
-
D.
accessPurpose
Indicates that one entity uses or accesses another entity specifically for a defined purpose or intended use.
-
E.
scriptPurpose
Indicates the intended function or role that a script is designed to perform.
- F. None of above. chosen
Provenance (4 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_69ef590b85a4819083ec7c12bd3c9c10 |
completed | April 27, 2026, 12:39 p.m. |
| NER | Named-entity recognition | batch_69f6397b64f881909d811225e57aac5e |
completed | May 2, 2026, 5:50 p.m. |
| PD | Predicate disambiguation | batch_69f6370c8c7c8190a02ea82847bb6e76 |
completed | May 2, 2026, 5:40 p.m. |
| PDg | Predicate description generation | batch_69f63893cc188190883ac9321a95d2dc |
completed | May 2, 2026, 5:46 p.m. |
Created at: April 27, 2026, 2:37 p.m.