Triple
T34872155
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Italian Regency of Carnaro |
E1005778
|
entity |
| Predicate | constitutionCoAuthor |
P2389
|
FINISHED |
| Object | Alceste De Ambris |
—
|
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: Alceste De Ambris | Statement: [Italian Regency of Carnaro, constitutionCoAuthor, Alceste De Ambris]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: constitutionCoAuthor Context triple: [Italian Regency of Carnaro, constitutionCoAuthor, Alceste De Ambris]
-
A.
constituentPeople
Indicates that certain people collectively make up or form part of a larger group, body, or organization.
-
B.
coAuthorNationality
Indicates that two or more co-authors of a work share the same nationality or have nationalities being related in the context of their co-authorship.
-
C.
amendmentAuthor
Indicates that one entity is the author or proposer of a specific amendment associated with another entity.
-
D.
hasCoauthor
chosen
Indicates that two or more entities have jointly authored the same work or publication.
-
E.
coAuthorField
Indicates that two or more entities have jointly authored a work within the same academic or professional field.
- 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_69f76dbde1c08190a24e7f9beb564c8d |
completed | May 3, 2026, 3:46 p.m. |
| NER | Named-entity recognition | batch_69fd509e6bc08190b263923c2f40fea3 |
completed | May 8, 2026, 2:55 a.m. |
| PD | Predicate disambiguation | batch_69fd4fd1a58881909d4b84de1b24e380 |
completed | May 8, 2026, 2:52 a.m. |
Created at: May 3, 2026, 4 p.m.