Triple
T11281748
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Silfra fissure |
E267080
|
entity |
| Predicate | waterFiltrationMedium |
P7405
|
FINISHED |
| Object | porous lava rock |
—
|
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: porous lava rock | Statement: [Silfra fissure, waterFiltrationMedium, porous lava rock]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: waterFiltrationMedium Context triple: [Silfra fissure, waterFiltrationMedium, porous lava rock]
-
A.
waterCondition
Indicates the state or quality of water affecting an entity, such as its cleanliness, safety, or suitability for a particular use.
-
B.
waterType
Indicates the specific kind or category of water associated with an entity (e.g., fresh, salt, brackish).
-
C.
waterFilled
Indicates that one entity is filled or occupied with water, typically to a certain level or capacity.
-
D.
waterInput
Indicates that an entity receives or is supplied with water from another source or system.
-
E.
waterExchangeThrough
chosen
Indicates a relationship where water is transferred or shared between entities through a specific medium, pathway, or mechanism.
- 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_69d6aac8c2f48190ad0596f1f89f0470 |
completed | April 8, 2026, 7:21 p.m. |
| NER | Named-entity recognition | batch_69d7e96e15708190b3a1cccfbbe65882 |
completed | April 9, 2026, 6:01 p.m. |
| PD | Predicate disambiguation | batch_69d787a240588190aa097298f951c915 |
completed | April 9, 2026, 11:04 a.m. |
Created at: April 8, 2026, 9:31 p.m.