Triple
T17456509
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Wolbachia |
E425041
|
entity |
| Predicate | localizationInHost |
P93283
|
FINISHED |
| Object | germline cells |
—
|
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: germline cells | Statement: [Wolbachia, localizationInHost, germline cells]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: localizationInHost Context triple: [Wolbachia, localizationInHost, germline cells]
-
A.
localization
chosen
Indicates the spatial or contextual placement of one entity relative to another or within a specific environment.
-
B.
localizationBy
Indicates a relationship where one entity determines, specifies, or constrains the spatial or contextual location of another entity.
-
C.
localizationSignal
Indicates that one entity provides or serves as a signal that directs the localization or spatial positioning of another entity.
-
D.
localizationInHuman
Indicates the anatomical or cellular location of something specifically within the human body.
-
E.
languageOfLocalization
Indicates the language into which something (such as software, content, or an interface) has been localized for use or display.
- 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_69d889db0ba481908402409af3b37917 |
completed | April 10, 2026, 5:25 a.m. |
| NER | Named-entity recognition | batch_69e45142b08481908cdd290692d796c3 |
completed | April 19, 2026, 3:51 a.m. |
| PD | Predicate disambiguation | batch_69e3b4f0e3fc819094e466b74622c956 |
completed | April 18, 2026, 4:44 p.m. |
Created at: April 10, 2026, 5:47 a.m.