Triple
T19878718
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Paris-Saclay cluster |
E477707
|
entity |
| Predicate | includesCompany |
P82128
|
FINISHED |
| Object | EDF |
—
|
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: EDF | Statement: [Paris-Saclay cluster, includesCompany, EDF]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: EDF Context triple: [Paris-Saclay cluster, includesCompany, EDF]
-
A.
EDF
chosen
EDF (Électricité de France) is France’s main state-owned electric utility company and one of the world’s largest producers and suppliers of electricity, particularly known for its extensive nuclear power operations.
-
B.
EDF
EDF is the acronym commonly used to refer to the Estonian Defence Forces, the military organization responsible for Estonia’s national defense.
-
C.
EDF
EDF is the IATA airport code for Joint Base Elmendorf–Richardson, a major U.S. military installation and airfield near Anchorage, Alaska.
-
D.
EDF
EDF is the European Union’s funding instrument designed to support collaborative research and development of defence technologies and capabilities among member states.
-
E.
EDF
EDF is a leading U.S.-based environmental advocacy organization known for its science-driven, market-based approaches to addressing climate change, pollution, and ecosystem protection.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69d8e51f32b08190b3687f4f60353250 |
completed | April 10, 2026, 11:55 a.m. |
| NER | Named-entity recognition | batch_69e658dd869c81908aed91ee767f5f3d |
completed | April 20, 2026, 4:48 p.m. |
Created at: April 10, 2026, 1:52 p.m.