Triple
T29062127
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Afdera town |
E735564
|
entity |
| Predicate | distanceToLakeAfrera |
P202207
|
FINISHED |
| Object | adjacent to Lake Afrera salt flats |
—
|
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: adjacent to Lake Afrera salt flats | Statement: [Afdera town, distanceToLakeAfrera, adjacent to Lake Afrera salt flats]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: distanceToLakeAfrera Context triple: [Afdera town, distanceToLakeAfrera, adjacent to Lake Afrera salt flats]
-
A.
distanceFromHornOfAfrica
Indicates the measured or specified distance between an entity and the Horn of Africa region.
-
B.
distanceFromNile
Indicates the spatial distance between a given location or entity and the Nile River.
-
C.
distanceFromFarafra
Indicates the measured spatial distance between a given entity and the location of Farafra.
-
D.
distanceToLakeTanganyika
Indicates the measured distance between a given entity’s location and Lake Tanganyika.
-
E.
distanceToSwakopmund
Indicates the spatial distance between a given entity’s location and the town of Swakopmund.
- F. None of above. chosen
Provenance (4 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_69f077e85498819088b65186550da8cd |
completed | April 28, 2026, 9:03 a.m. |
| NER | Named-entity recognition | batch_6a0062e6bd788190a7b4f3e5befb5cbb |
completed | May 10, 2026, 10:50 a.m. |
| PD | Predicate disambiguation | batch_6a0061989d188190b4815b2de3e8676f |
completed | May 10, 2026, 10:44 a.m. |
| PDg | Predicate description generation | batch_6a0062e60b648190b59ea90cb7918b9a |
completed | May 10, 2026, 10:50 a.m. |
Created at: April 28, 2026, 10:15 a.m.