Triple
T10179928
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 2022 French presidential election |
E235957
|
entity |
| Predicate | politicalLandscape |
P2456
|
FINISHED |
| Object | fragmented |
—
|
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: fragmented | Statement: [2022 French presidential election, politicalLandscape, fragmented]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: politicalLandscape Context triple: [2022 French presidential election, politicalLandscape, fragmented]
-
A.
politicalTheme
Indicates that something is related to, characterized by, or primarily concerned with politics, governance, or political issues.
-
B.
politicalSphere
Indicates involvement or relevance within the domain of politics, governance, or public policy activities and interactions.
-
C.
politicalCategory
Indicates the political classification or ideological grouping that an entity belongs to or is associated with.
-
D.
politicalPattern
chosen
Indicates a recurring or characteristic way in which political behaviors, decisions, or power dynamics are organized or expressed.
-
E.
politicalCurrent
Indicates that an entity is presently holding or engaged in a specific political role, status, or activity at the current time.
- 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_69ca84d1d5f88190ab878a1021ecff68 |
completed | March 30, 2026, 2:12 p.m. |
| NER | Named-entity recognition | batch_69cdecd7ed608190bfdec8b61cc99205 |
completed | April 2, 2026, 4:13 a.m. |
| PD | Predicate disambiguation | batch_69cd7c79f21c8190a7f31b2eab80b8ba |
completed | April 1, 2026, 8:13 p.m. |
Created at: March 30, 2026, 9:11 p.m.