Triple
T27494538
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Phyllostylon rhamnoides |
E693986
|
entity |
| Predicate | woodResistance |
P1357
|
FINISHED |
| Object | resistant to wear |
—
|
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: resistant to wear | Statement: [Phyllostylon rhamnoides, woodResistance, resistant to wear]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: woodResistance Context triple: [Phyllostylon rhamnoides, woodResistance, resistant to wear]
-
A.
woodProperty
chosen
Indicates that one entity specifies or characterizes a property or attribute of wood associated with another entity.
-
B.
hasWood
Indicates that one entity possesses, contains, or is made of wood in relation to another entity or context.
-
C.
woodSimilarTo
Indicates that one wood is similar to another in relevant characteristics such as type, appearance, or properties.
-
D.
topWood
Indicates that one entity is made of or features a particular type of wood used specifically for its top surface or top section.
-
E.
isWoodenStructure
Indicates that the subject is a structure primarily made of wood or constructed using wooden components.
- 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_69ef5382b9648190be0b1ef2ad5d043c |
completed | April 27, 2026, 12:16 p.m. |
| NER | Named-entity recognition | batch_69f62e8cb0c48190bbd8647a1fb6635b |
completed | May 2, 2026, 5:04 p.m. |
| PD | Predicate disambiguation | batch_69f623aaf40081909f947431424a1d55 |
completed | May 2, 2026, 4:17 p.m. |
Created at: April 27, 2026, 1:07 p.m.