Triple
T11163008
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Autoroute A4 |
E264086
|
entity |
| Predicate | maintainedBy |
P86
|
FINISHED |
| Object | SANEF |
E237834
|
NE 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: SANEF | Statement: [Autoroute A4, maintainedBy, SANEF]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: SANEF Context triple: [Autoroute A4, maintainedBy, SANEF]
-
A.
SANEF
chosen
SANEF is a major French motorway concession and operating company responsible for managing and maintaining several toll highways in northern and eastern France.
-
B.
SAFN
SAFN is a professional organization dedicated to advancing the anthropological study of food, nutrition, and related cultural practices.
-
C.
Safis
The Safis are a Pashtun tribal group historically associated with the Mohmand region along the Afghanistan–Pakistan border.
-
D.
SDF
SDF is the acronym for the SAARC Development Fund, a regional financial institution that supports social, economic, and infrastructure development projects among South Asian Association for Regional Cooperation member countries.
-
E.
SDF
SDF is the IATA airport code for Louisville Muhammad Ali International Airport, a major air cargo and passenger hub serving Louisville, Kentucky.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69d6aa9ccddc8190868998c8b7beb060 |
completed | April 8, 2026, 7:21 p.m. |
| NER | Named-entity recognition | batch_69d7e8832fe88190a74d81f9ed547baa |
completed | April 9, 2026, 5:57 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69e46375c61c8190939401f790cf1593 |
completed | April 19, 2026, 5:09 a.m. |
Created at: April 8, 2026, 9:29 p.m.