Triple
T16789096
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Nematomorpha |
E408056
|
entity |
| Predicate | typicalHosts |
P40204
|
FINISHED |
| Object | insects |
—
|
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: insects | Statement: [Nematomorpha, typicalHosts, insects]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typicalHosts Context triple: [Nematomorpha, typicalHosts, insects]
-
A.
typicalHostSelection
Indicates the usual or preferred choice of host entity that is selected in a given context or process.
-
B.
primaryHosts
chosen
Indicates that the subject serves as the main or principal host for the object, such as an organism, event, or service.
-
C.
typicalHostRegion
Indicates the geographic region where a host is most commonly or characteristically found or associated.
-
D.
featuresHosts
Indicates that one entity serves as the host or platform on which another entity is presented, run, or made available.
-
E.
typicalDomain
Indicates that one entity is the characteristic or most common domain, context, or area of application in which another entity typically occurs or is used.
- 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_69d8839270588190886720d9519bbf8f |
completed | April 10, 2026, 4:58 a.m. |
| NER | Named-entity recognition | batch_69e3b2a50e18819090a30e1f38e520e0 |
completed | April 18, 2026, 4:34 p.m. |
| PD | Predicate disambiguation | batch_69e319cf691c819083e39225f5777ef0 |
completed | April 18, 2026, 5:42 a.m. |
Created at: April 10, 2026, 5:22 a.m.