Triple
T29355474
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Snares Islands |
E744427
|
entity |
| Predicate | endemicPlant |
P954
|
FINISHED |
| Object |
Olearia lyallii
Olearia lyallii is a species of large, daisy-like flowering shrub or small tree native to New Zealand’s subantarctic region, notable for forming dense coastal forests on remote islands.
|
E1864321
|
NE FINISHED |
How this triple was built (3 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: Olearia lyallii | Statement: [Snares Islands, endemicPlant, Olearia lyallii]
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Olearia lyallii Triple: [Snares Islands, endemicPlant, Olearia lyallii]
Generated description
Olearia lyallii is a species of large, daisy-like flowering shrub or small tree native to New Zealand’s subantarctic region, notable for forming dense coastal forests on remote islands.
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: endemicPlant Context triple: [Snares Islands, endemicPlant, Olearia lyallii]
-
A.
hasEndemicSpecies
chosen
Indicates that a place or region contains species that are native to and found only within that specific geographic area.
-
B.
ecotypeOf
Indicates that one entity is an ecotype, i.e., a locally adapted variant or form, of another entity within the same species.
-
C.
hostsPlantOf
Indicates that one entity serves as a host environment or substrate on which a particular plant lives, grows, or depends.
-
D.
associatedFlora
Indicates a relationship where specific plants or vegetation are characteristically linked to, occur with, or are commonly found in association with a given entity or environment.
-
E.
studiedFloraOf
Indicates that a subject conducted research or examination on the plant life (flora) of a specified object or region.
- F. None of above.
Provenance (6 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_69f0a79aee588190b490f19d93c6e52d |
completed | April 28, 2026, 12:27 p.m. |
| NER | Named-entity recognition | batch_69f6695ea2c0819098c94eb40d2a0634 |
completed | May 2, 2026, 9:15 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a25c0f529188190b99a890e097b841b |
completed | June 7, 2026, 7:05 p.m. |
| NEDg | Description generation | batch_6a25c4f14e108190a8e492f95a1af9b0 |
completed | June 7, 2026, 7:22 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a25c93893f88190b77d1054320288dd |
completed | June 7, 2026, 7:40 p.m. |
| PD | Predicate disambiguation | batch_69f660f4f7a88190b93c60d76b86c912 |
completed | May 2, 2026, 8:39 p.m. |
Created at: April 28, 2026, 2:11 p.m.