Triple
T23835818
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Melanconis |
E590849
|
entity |
| Predicate | taxonAuthority |
P7386
|
FINISHED |
| Object |
Tulasne & C. Tulasne
Tulasne & C. Tulasne refers to the French mycologist brothers Louis René Tulasne and Charles Tulasne, renowned for their pioneering 19th-century work in fungal taxonomy and morphology.
|
E1603212
|
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: Tulasne & C. Tulasne | Statement: [Melanconis, taxonAuthority, Tulasne & C. Tulasne]
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: Tulasne & C. Tulasne Triple: [Melanconis, taxonAuthority, Tulasne & C. Tulasne]
Generated description
Tulasne & C. Tulasne refers to the French mycologist brothers Louis René Tulasne and Charles Tulasne, renowned for their pioneering 19th-century work in fungal taxonomy and morphology.
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: taxonAuthority Context triple: [Melanconis, taxonAuthority, Tulasne & C. Tulasne]
-
A.
taxonomicAuthority
chosen
Indicates the entity that formally described, named, or classified another entity in a taxonomic context.
-
B.
namedTaxon
Indicates that an entity is identified as, or associated with, a particular taxonomic name.
-
C.
speciesEponym
Indicates that a species is named in honor of a particular person or entity.
-
D.
authorTraditionallyAscribedTo
Indicates that authorship of a work is customarily or historically attributed to an entity, even if definitive proof of authorship may be uncertain or disputed.
-
E.
isTaxonAuthoritativeLanguage
Indicates that a particular language is recognized as the official or authoritative language used for naming or describing a taxon.
- 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_69e25d1de32c8190a907afe9c3d6cd6d |
completed | April 17, 2026, 4:17 p.m. |
| NER | Named-entity recognition | batch_69f1c7f9eaa081909531f1322e0ec9ca |
completed | April 29, 2026, 8:57 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0f69a115808190b25202b48aa7cef6 |
completed | May 21, 2026, 8:22 p.m. |
| NEDg | Description generation | batch_6a0f6d4007308190b2d474963d0a9b8c |
completed | May 21, 2026, 8:38 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a0f6e0619388190b88e0d10c5f46934 |
completed | May 21, 2026, 8:41 p.m. |
| PD | Predicate disambiguation | batch_69f156036ad48190bc2ffdaf39218bcb |
completed | April 29, 2026, 12:51 a.m. |
Created at: April 17, 2026, 8:07 p.m.