Triple
T13537277
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | EU directives |
E323292
|
entity |
| Predicate | usuallyCitedAs |
P60904
|
FINISHED |
| Object | Directive followed by year and number |
—
|
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: Directive followed by year and number | Statement: [EU directives, usuallyCitedAs, Directive followed by year and number]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: usuallyCitedAs Context triple: [EU directives, usuallyCitedAs, Directive followed by year and number]
-
A.
oftenCitedAs
chosen
Indicates that one entity is frequently referenced or mentioned as an example, source, or authority in relation to another entity.
-
B.
usedAsAuthorCitationFor
Indicates that one entity is cited or referenced as the author in the bibliographic citation of another entity.
-
C.
citationAs
Indicates that one entity is cited or referenced in the role or capacity specified by another entity (such as a particular work, version, or context).
-
D.
citationIn
Indicates that one work cites, references, or otherwise acknowledges another work as a source.
-
E.
citationOf
Indicates that one entity cites, references, or formally acknowledges another entity as a source.
- 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_69d8076776248190bdf0d4fa1f85a5fc |
completed | April 9, 2026, 8:09 p.m. |
| NER | Named-entity recognition | batch_69dbafbe39948190808062d4eff91841 |
completed | April 12, 2026, 2:44 p.m. |
| PD | Predicate disambiguation | batch_69dbae1046c48190b4ee98c6c9cb9d85 |
completed | April 12, 2026, 2:37 p.m. |
Created at: April 9, 2026, 9:45 p.m.