Triple
T227336
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Congo River mouth |
E4339
|
entity |
| Predicate | hasApproximateDepth |
P9310
|
FINISHED |
| Object | over 200 meters in some areas |
—
|
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: over 200 meters in some areas | Statement: [Congo River mouth, hasApproximateDepth, over 200 meters in some areas]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasApproximateDepth Context triple: [Congo River mouth, hasApproximateDepth, over 200 meters in some areas]
-
A.
hasAverageDepth
Indicates that an entity possesses a specified mean depth value, typically measured over its entire extent or area.
-
B.
hasMaximumDepth
Indicates that an entity possesses a greatest or limiting depth value beyond which it does not extend.
-
C.
hasApproximateDuration
Indicates that one entity has a duration that is estimated or not exact, typically expressed as an approximate length of time.
-
D.
maximumDepth
Indicates the greatest extent or deepest level reached by something within a given context or structure.
-
E.
hasApproximateVendorCount
Indicates that an entity is associated with an estimated or non-exact number of vendors.
- 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_69a257363ffc81909757bde7ab3404da |
completed | Feb. 28, 2026, 2:47 a.m. |
| NER | Named-entity recognition | batch_69a25d10ac248190a98dedabf5358668 |
completed | Feb. 28, 2026, 3:12 a.m. |
| PD | Predicate disambiguation | batch_69a25b5877588190af694d060377f027 |
completed | Feb. 28, 2026, 3:04 a.m. |
| PDg | Predicate description generation | batch_69a25d0ec71081908478c800be4f7bb0 |
completed | Feb. 28, 2026, 3:12 a.m. |
Created at: Feb. 28, 2026, 2:53 a.m.