Triple
T17244259
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Deadvlei |
E418580
|
entity |
| Predicate | near |
P350
|
FINISHED |
| Object | Dune 45 |
E414858
|
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: Dune 45 | Statement: [Deadvlei, near, Dune 45]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Dune 45 Context triple: [Deadvlei, near, Dune 45]
-
A.
Dune 45
chosen
Dune 45 is a famously photogenic, sharply contoured sand dune in Namibia’s Namib Desert, renowned for its striking sunrise and sunset views.
-
B.
Dune Helgoland
Dune Helgoland is a small sandy island off the German North Sea coast known for its seal colonies, birdlife, and role as a site for marine biological research.
-
C.
Dune: The Sisterhood
Dune: The Sisterhood is a television series set in the Dune universe that focuses on the origins and rise of the Bene Gesserit sisterhood.
-
D.
Dune
Dune is a landmark science fiction novel by Frank Herbert, renowned for its intricate world-building, political intrigue, and exploration of ecology, religion, and power.
-
E.
Dune
Dune is the desert planet central to Frank Herbert's science fiction universe, famed for its harsh environment and the valuable spice melange found in its sands.
- 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_69d886d8e96081909870bff6c3d0bf09 |
completed | April 10, 2026, 5:12 a.m. |
| NER | Named-entity recognition | batch_69e42e22fb2c8190aea5d3872095bf46 |
completed | April 19, 2026, 1:21 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0170f5582c81908efb7a369a096aeb |
completed | May 11, 2026, 6:02 a.m. |
Created at: April 10, 2026, 5:39 a.m.