Triple
T12319271
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Pyrus calleryana |
E293684
|
entity |
| Predicate | dispersalAgent |
P43554
|
FINISHED |
| Object | birds |
—
|
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: birds | Statement: [Pyrus calleryana, dispersalAgent, birds]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: dispersalAgent Context triple: [Pyrus calleryana, dispersalAgent, birds]
-
A.
seedDispersal
Indicates the process by which seeds are transported away from the parent organism to new locations, often via wind, water, or animals.
-
B.
dispersalVector
chosen
Indicates the means or agent by which something (such as an organism, propagule, or substance) is spread or transported from one location to another.
-
C.
dispersalUnit
Indicates the type or form of unit in which something (such as seeds, spores, or organisms) is spread or dispersed from one place to another.
-
D.
dispersingElement
Indicates that one entity causes another entity to spread out or scatter from a concentrated state into a wider area or among multiple parts.
-
E.
crossDisperser
Indicates that one entity functions as a cross disperser, separating different wavelengths or components of another entity’s output or signal.
- 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_69d6ab6ae0dc8190b1522a9c1c55c114 |
completed | April 8, 2026, 7:24 p.m. |
| NER | Named-entity recognition | batch_69d93f621570819091ee1db2609233ea |
completed | April 10, 2026, 6:20 p.m. |
| PD | Predicate disambiguation | batch_69d93ec5be788190b82d2edc6a0f1095 |
completed | April 10, 2026, 6:17 p.m. |
Created at: April 8, 2026, 9:53 p.m.