Triple
T3922968
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Staurozoa |
E93203
|
entity |
| Predicate | bodyOrientation |
P40589
|
FINISHED |
| Object | oral surface directed upward |
—
|
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: oral surface directed upward | Statement: [Staurozoa, bodyOrientation, oral surface directed upward]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: bodyOrientation Context triple: [Staurozoa, bodyOrientation, oral surface directed upward]
-
A.
bodySideOrientation
Indicates the spatial relationship of an entity with respect to the left, right, or bilateral side of a body.
-
B.
sessionOrientation
Indicates the directional or spatial alignment relationship established between entities within a session or interaction context.
-
C.
hasFieldOrientation
Indicates that one entity has a specified directional or spatial orientation relative to a field (such as magnetic, electric, or visual field).
-
D.
pouchOrientation
Indicates the spatial direction or alignment of a pouch relative to a reference frame or object.
-
E.
surfaceOrientation
chosen
Indicates the spatial orientation or facing direction of a surface relative to a reference frame or viewpoint.
- 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_69aed96bfa1081908f7b30f2c647dee6 |
completed | March 9, 2026, 2:30 p.m. |
| NER | Named-entity recognition | batch_69aeed7c2c848190a6d62e2df9b942d4 |
completed | March 9, 2026, 3:55 p.m. |
| PD | Predicate disambiguation | batch_69aee7609c4081908000ce12ae827c3f |
completed | March 9, 2026, 3:29 p.m. |
Created at: March 9, 2026, 3:22 p.m.