Triple
T30036145
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kalkaska sand |
E763162
|
entity |
| Predicate | soilOrder |
P168373
|
FINISHED |
| Object |
Spodosols
Spodosols are acidic, nutrient-poor soils typically found in cool, humid regions under coniferous forests, characterized by a leached, ash-colored layer overlying a dark, organic- and iron-rich subsoil horizon.
|
E1895888
|
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: Spodosols | Statement: [Kalkaska sand, soilOrder, Spodosols]
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: Spodosols Triple: [Kalkaska sand, soilOrder, Spodosols]
Generated description
Spodosols are acidic, nutrient-poor soils typically found in cool, humid regions under coniferous forests, characterized by a leached, ash-colored layer overlying a dark, organic- and iron-rich subsoil horizon.
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: soilOrder Context triple: [Kalkaska sand, soilOrder, Spodosols]
-
A.
soilPreference
Indicates the type or condition of soil that an entity prefers or is best suited to grow or exist in.
-
B.
soilOrigin
Indicates the source or provenance from which a given soil was formed or obtained.
-
C.
soilRepresents
Indicates that one soil sample, type, or condition stands for, symbolizes, or serves as a proxy for another soil-related state or concept.
-
D.
soilFertility
Indicates the level or quality of nutrients and conditions in soil that affect its ability to support plant growth.
-
E.
hasSoil
Indicates that one entity possesses, contains, or is associated with a particular type or instance of soil.
- F. None of above. chosen
Provenance (7 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_69f2246fb2b88190acff36bf7975c8f0 |
completed | April 29, 2026, 3:32 p.m. |
| NER | Named-entity recognition | batch_69f679d44f2081908ffa58a7709907ba |
completed | May 2, 2026, 10:25 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a273237a5988190bc3951487b98ce52 |
completed | June 8, 2026, 9:20 p.m. |
| NEDg | Description generation | batch_6a273425663c819088dc47e7ee8e0fa5 |
completed | June 8, 2026, 9:29 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a2734f30d1c8190869904ea95f5f74f |
completed | June 8, 2026, 9:32 p.m. |
| PD | Predicate disambiguation | batch_69f66ec9919881908a187bfc7c4df192 |
completed | May 2, 2026, 9:38 p.m. |
| PDg | Predicate description generation | batch_69f67256d064819094be04fc1bbbc635 |
completed | May 2, 2026, 9:53 p.m. |
Created at: April 29, 2026, 6:51 p.m.