Triple
T28100000
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Congrès de Tours de 1920 |
E710204
|
entity |
| Predicate | aboutitÀ |
P380
|
FINISHED |
| Object | fondation du Parti communiste français |
—
|
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: fondation du Parti communiste français | Statement: [Congrès de Tours de 1920, aboutitÀ, fondation du Parti communiste français]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: aboutitÀ Context triple: [Congrès de Tours de 1920, aboutitÀ, fondation du Parti communiste français]
-
A.
isAbout
chosen
Indicates that one entity has as its subject, focus, or primary concern the content, topic, or theme represented by another entity.
-
B.
saidAbout
Indicates that a statement or assertion has been made concerning or in reference to a particular entity or subject.
-
C.
aboutPlace
Indicates that something (such as a statement, work, or information) concerns, describes, or is thematically related to a particular place or location.
-
D.
aboutProgram
Indicates that something (such as a document, message, or statement) concerns, discusses, or is related to a particular program.
-
E.
aboutTeam
Indicates that something concerns, relates to, or is associated with a particular team.
- 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_69ef9b70fd108190a875953b2e50ca91 |
completed | April 27, 2026, 5:22 p.m. |
| NER | Named-entity recognition | batch_69f65876c52c8190bc889c7a67bd07f3 |
completed | May 2, 2026, 8:03 p.m. |
| PD | Predicate disambiguation | batch_69f6575d89788190aca478e4aea05a65 |
completed | May 2, 2026, 7:58 p.m. |
Created at: April 27, 2026, 9:04 p.m.