Triple
T31643618
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ancistrus cirrhosus |
E807523
|
entity |
| Predicate | maintenanceInCaptivity |
P182421
|
FINISHED |
| Object | kept in community aquariums |
—
|
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: kept in community aquariums | Statement: [Ancistrus cirrhosus, maintenanceInCaptivity, kept in community aquariums]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: maintenanceInCaptivity Context triple: [Ancistrus cirrhosus, maintenanceInCaptivity, kept in community aquariums]
-
A.
maintenance
Indicates that an entity performs, requires, or is involved in upkeep, repair, or preservation activities for another entity or system.
-
B.
maintenanceEvent
Indicates that a maintenance-related action or occurrence takes place involving one or more entities.
-
C.
maintenanceType
Indicates the specific category or kind of maintenance activity associated with an entity or relationship.
-
D.
maintenanceFeature
Indicates that one entity serves as a maintenance-related feature, capability, or component associated with another entity.
-
E.
maintenanceNote
Indicates that there is a note or comment documenting information, instructions, or observations related to the maintenance of an entity.
- 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_69f348d9ce58819093ea2da83cbeeec1 |
completed | April 30, 2026, 12:19 p.m. |
| NER | Named-entity recognition | batch_69f78d7211a48190bfb59c406f0bf12f |
completed | May 3, 2026, 6:01 p.m. |
| PD | Predicate disambiguation | batch_69f78b8cb3a881909ebaac1b503988c2 |
completed | May 3, 2026, 5:53 p.m. |
| PDg | Predicate description generation | batch_69f78c6014e08190864785a4fe3e8e73 |
completed | May 3, 2026, 5:56 p.m. |
Created at: April 30, 2026, 10:50 p.m.