Triple
T31241391
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dendrophylax lindenii |
E796569
|
entity |
| Predicate | photosynthesisOrgan |
P12081
|
FINISHED |
| Object | roots |
—
|
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: roots | Statement: [Dendrophylax lindenii, photosynthesisOrgan, roots]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: photosynthesisOrgan Context triple: [Dendrophylax lindenii, photosynthesisOrgan, roots]
-
A.
photosyntheticOrgan
chosen
Indicates that an entity is an organ specialized for performing photosynthesis in an organism.
-
B.
photosyntheticOrganism
Indicates that an organism performs photosynthesis, converting light energy into chemical energy to sustain itself.
-
C.
photosynthesisType
Indicates the specific kind or category of photosynthesis an organism performs (e.g., C3, C4, CAM).
-
D.
photosyntheticTissue
Indicates that an entity has tissue capable of performing photosynthesis, converting light energy into chemical energy.
-
E.
plant
Indicates that an entity places or sets something firmly in or on a location, often so it will grow, remain fixed, or be established there.
- 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_69f224db69ac81909a370adad6a7ac7c |
completed | April 29, 2026, 3:33 p.m. |
| NER | Named-entity recognition | batch_69f69dfdda708190be290c7bec205445 |
completed | May 3, 2026, 12:59 a.m. |
| PD | Predicate disambiguation | batch_69f69d1a37e081908d1d86b90ff502bd |
completed | May 3, 2026, 12:55 a.m. |
Created at: April 29, 2026, 9:11 p.m.