Triple
T35249739
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ventotene (comune) |
E1018062
|
entity |
| Predicate | hasDocumentComposedThere |
P112098
|
FINISHED |
| Object | Ventotene Manifesto |
—
|
NE NERFINISHED |
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: Ventotene Manifesto | Statement: [Ventotene (comune), hasDocumentComposedThere, Ventotene Manifesto]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasDocumentComposedThere Context triple: [Ventotene (comune), hasDocumentComposedThere, Ventotene Manifesto]
-
A.
hasCompositionBy
Indicates that something (such as a work or piece) is composed or created by a particular composer or author.
-
B.
isComposedIn
chosen
Indicates that something is created, written, or formed within a particular context, medium, or framework.
-
C.
previouslyComposedOf
Indicates that something was formerly made up of or constituted by certain parts, elements, or members, but no longer is.
-
D.
hasCompositionalFocus
Indicates that one entity is the primary subject or focal element within the compositional structure of another entity.
-
E.
hasDocumentContext
Indicates that a document is associated with, or interpreted within, a specific contextual framework or situation.
- 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_69f76de407d081909dfc3c419817ae93 |
completed | May 3, 2026, 3:46 p.m. |
| NER | Named-entity recognition | batch_69fb2e940d5c8190bceae77daf4ef512 |
completed | May 6, 2026, 12:05 p.m. |
| PD | Predicate disambiguation | batch_69f9fec70bd881909c658a3c5020318b |
completed | May 5, 2026, 2:29 p.m. |
Created at: May 3, 2026, 4:02 p.m.