Triple
T16920539
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | ELA-4 |
E410433
|
entity |
| Predicate | locatedNear |
P294
|
FINISHED |
| Object | Kourou |
E155694
|
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: Kourou | Statement: [ELA-4, locatedNear, Kourou]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Kourou Context triple: [ELA-4, locatedNear, Kourou]
-
A.
Kourou
chosen
Kourou is a coastal town in French Guiana best known as the site of the Guiana Space Centre, a major European spaceport.
-
B.
Guiana Space Centre
The Guiana Space Centre is a major European spaceport located in French Guiana, used for launching a wide range of commercial and scientific missions including flagship observatories.
-
C.
Baikonur
Baikonur is a town in Kazakhstan historically associated with the Soviet and Russian space programs, giving its name to the nearby Baikonur Cosmodrome.
-
D.
Baikonur
Baikonur is a metro station on the Almaty Metro system in Almaty, Kazakhstan.
-
E.
Cidade do Maio
Cidade do Maio is the main urban center and administrative capital of Maio Island in Cape Verde, known for its coastal setting and role as the island’s political and economic hub.
- 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_69d886c7b1e481908c3766dfa8c13458 |
completed | April 10, 2026, 5:12 a.m. |
| NER | Named-entity recognition | batch_69e3cdee252c81908621b2ca897416e9 |
completed | April 18, 2026, 6:31 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a00d45a6ee8819092ae7c572be68e62 |
completed | May 10, 2026, 6:54 p.m. |
Created at: April 10, 2026, 5:30 a.m.