Triple
T321329
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Archaea |
E6420
|
entity |
| Predicate | biotechnologicalUses |
P8461
|
FINISHED |
| Object | thermostable enzymes |
—
|
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: thermostable enzymes | Statement: [Archaea, biotechnologicalUses, thermostable enzymes]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: biotechnologicalUses Context triple: [Archaea, biotechnologicalUses, thermostable enzymes]
-
A.
usedInIndustry
chosen
Indicates that something is employed or applied within a particular industry or industrial sector.
-
B.
notableUse
Indicates that something is prominently or famously used by a particular entity, context, or for a specific purpose.
-
C.
economicUse
Indicates that one entity utilizes another for economic purposes, such as production, trade, revenue generation, or cost-saving activities.
-
D.
isBiodegradable
Indicates that a material or substance can be broken down naturally by microorganisms into simpler, non-harmful components over time.
-
E.
traditionalUse
Indicates that something is used or practiced according to long-established customs, habits, or cultural traditions.
- 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_69a2e7933d6c8190bb2592ad13286ef2 |
completed | Feb. 28, 2026, 1:03 p.m. |
| NER | Named-entity recognition | batch_69a2ea81a1e88190b3496070eb3d85f5 |
completed | Feb. 28, 2026, 1:15 p.m. |
| PD | Predicate disambiguation | batch_69a2e948048c819098ba4de9261ef2ef |
completed | Feb. 28, 2026, 1:10 p.m. |
Created at: Feb. 28, 2026, 1:08 p.m.