Triple
T28937508
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mazaceae |
E730355
|
entity |
| Predicate | mostlyIncludes |
P95472
|
FINISHED |
| Object | herbaceous species |
—
|
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: herbaceous species | Statement: [Mazaceae, mostlyIncludes, herbaceous species]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: mostlyIncludes Context triple: [Mazaceae, mostlyIncludes, herbaceous species]
-
A.
includes
Indicates that one entity contains, encompasses, or has another entity as a part, member, or subset.
-
B.
sometimesIncluded
Indicates that one entity is occasionally, but not always, contained within, part of, or present in association with another entity.
-
C.
typicallyContain
chosen
Indicates that one entity is normally or commonly found within, included in, or held by another entity under usual circumstances.
-
D.
aimedToInclude
Indicates that one entity intentionally sought to have another entity or element contained or incorporated within it.
-
E.
mostlyIn
Indicates that one entity is contained or located within another entity to a predominant or greater extent, though not necessarily entirely.
- 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_69f043ea0aa88190a25acbf46157995a |
completed | April 28, 2026, 5:21 a.m. |
| NER | Named-entity recognition | batch_69f65b809be4819081a3ae8def7bbdc1 |
completed | May 2, 2026, 8:16 p.m. |
| PD | Predicate disambiguation | batch_69f659d02f1c8190831758ac52bb54e4 |
completed | May 2, 2026, 8:08 p.m. |
Created at: April 28, 2026, 8:33 a.m.