Triple
T33960788
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Gaviidae |
E870708
|
entity |
| Predicate | bodyMassCharacteristic |
P62520
|
FINISHED |
| Object | relatively heavy-bodied for diving |
—
|
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: relatively heavy-bodied for diving | Statement: [Gaviidae, bodyMassCharacteristic, relatively heavy-bodied for diving]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: bodyMassCharacteristic Context triple: [Gaviidae, bodyMassCharacteristic, relatively heavy-bodied for diving]
-
A.
primaryBodyType
Indicates the main physical form or category that characterizes an entity’s overall body structure or composition.
-
B.
bodyThickness
Indicates the measured or relative thickness of an entity’s body in the context of a comparison or description.
-
C.
managementBodyType
Indicates the type or category of governing or management body responsible for overseeing an entity.
-
D.
physicalCharacteristics
chosen
Indicates that one entity has or describes the bodily or material attributes, features, or appearance of another entity.
-
E.
residesOverBodyType
Indicates that one entity is positioned or located above another entity that is characterized by a specific body type.
- 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_69f3499ce8e88190b66e1d49ad8c7037 |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_69f7064e906881909c3186c646145d34 |
completed | May 3, 2026, 8:24 a.m. |
| PD | Predicate disambiguation | batch_69f70100ec1c8190a6b97f50e88891f2 |
completed | May 3, 2026, 8:02 a.m. |
Created at: May 1, 2026, 1:50 a.m.