Triple
T35112674
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | David Salo |
E1013337
|
entity |
| Predicate | languageSpecialization |
P152559
|
FINISHED |
| Object | Sindarin |
—
|
NE NERFINISHED |
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: Sindarin | Statement: [David Salo, languageSpecialization, Sindarin]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: languageSpecialization Context triple: [David Salo, languageSpecialization, Sindarin]
-
A.
primaryLanguageSpecialization
Indicates the main language in which an entity has specialized knowledge, focus, or expertise.
-
B.
languageSubject
chosen
Indicates that a particular language is the subject or topic being studied, discussed, or otherwise focused on in relation to another entity.
-
C.
languageSpecifies
Indicates that one entity defines or constrains the syntax, semantics, or usage rules that govern how another language or linguistic system is expressed or interpreted.
-
D.
languageCategory
Indicates the classification relationship where a language is assigned to a particular linguistic or functional category.
-
E.
subjectSpecialization
Indicates that one subject focuses on, or has expertise in, a particular field, topic, or area of knowledge.
- 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_69f76dd659d08190bcdc00d37caafb62 |
completed | May 3, 2026, 3:46 p.m. |
| NER | Named-entity recognition | batch_6a00af6b3a948190a92813c13384c304 |
completed | May 10, 2026, 4:16 p.m. |
| PD | Predicate disambiguation | batch_6a00aec35610819085dd5137715a4228 |
completed | May 10, 2026, 4:13 p.m. |
Created at: May 3, 2026, 4:01 p.m.