Triple
T16991372
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tilio-Acerion ravine forests |
E412200
|
entity |
| Predicate | typicalFungiComponent |
P126070
|
FINISHED |
| Object | saprotrophic wood-decaying fungi |
—
|
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: saprotrophic wood-decaying fungi | Statement: [Tilio-Acerion ravine forests, typicalFungiComponent, saprotrophic wood-decaying fungi]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typicalFungiComponent Context triple: [Tilio-Acerion ravine forests, typicalFungiComponent, saprotrophic wood-decaying fungi]
-
A.
criterionForFungi
Indicates a condition or standard that is used to identify, classify, or evaluate fungi.
-
B.
fruitingBodyType
Indicates the type or form of the fruiting body produced by an organism (e.g., mushroom, puffball, bracket).
-
C.
isLargestFungalPhylum
Indicates that the subject phylum is the largest among all fungal phyla, typically in terms of number of species.
-
D.
hymeniumType
Indicates the type or structure of the spore-bearing surface (hymenium) in a fungus, describing how and where its reproductive cells are arranged.
-
E.
fruitingBodyColor
Indicates the color or coloration pattern of an organism’s fruiting body (the spore-producing structure).
- F. None of above. chosen
Provenance (4 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_69d886cb581c8190ab05f4b429c9cd85 |
completed | April 10, 2026, 5:12 a.m. |
| NER | Named-entity recognition | batch_69e3d280e3348190a27bd5dc7cf87c0e |
completed | April 18, 2026, 6:50 p.m. |
| PD | Predicate disambiguation | batch_69e35d552bc08190af17ef7659e094ef |
completed | April 18, 2026, 10:30 a.m. |
| PDg | Predicate description generation | batch_69e378e037c88190935d732e0f10d5d7 |
completed | April 18, 2026, 12:28 p.m. |
Created at: April 10, 2026, 5:32 a.m.