Triple
T33720977
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Neostethus |
E864010
|
entity |
| Predicate | bodyWater |
P118641
|
FINISHED |
| Object | freshwater streams |
—
|
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: freshwater streams | Statement: [Neostethus, bodyWater, freshwater streams]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: bodyWater Context triple: [Neostethus, bodyWater, freshwater streams]
-
A.
bodyWaterClaimedBy
Indicates that a particular body of water is asserted or designated as being owned, controlled, or claimed by a specific entity.
-
B.
hydrationSupport
Indicates that one entity provides or enhances the hydration of another entity, helping to maintain or improve its water balance.
-
C.
hydrationState
chosen
Indicates the current level or condition of how much water or fluid an entity contains or has available.
-
D.
waterVolume
Indicates the amount of water present in or associated with an entity, typically measured as a volume.
-
E.
bodyThickness
Indicates the measured or relative thickness of an entity’s body in the context of a comparison or description.
- F. None of above.
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_69f34989871c81908682e22a2fe4b829 |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_69f6ffbad8848190867c2988c0ceb84f |
completed | May 3, 2026, 7:56 a.m. |
| PD | Predicate disambiguation | batch_69f6fc5740fc81909774a4f65201a3ff |
completed | May 3, 2026, 7:42 a.m. |
Created at: May 1, 2026, 1:44 a.m.