Triple
T1845004
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Salasaca Kichwa |
E41264
|
entity |
| Predicate | sharesVocabularyWith |
P2268
|
FINISHED |
| Object | other Ecuadorian Kichwa dialects |
—
|
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: other Ecuadorian Kichwa dialects | Statement: [Salasaca Kichwa, sharesVocabularyWith, other Ecuadorian Kichwa dialects]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: sharesVocabularyWith Context triple: [Salasaca Kichwa, sharesVocabularyWith, other Ecuadorian Kichwa dialects]
-
A.
sharesSpellingWith
Indicates that two entities have identical or substantially identical written forms (i.e., they are spelled the same way).
-
B.
sharesMeaningWith
Indicates that two expressions convey the same or very similar meaning, even if they differ in form or wording.
-
C.
sharesEtymologyWith
Indicates that two terms originate from the same linguistic root or source word, or have closely related historical word origins.
-
D.
hasCommonLoanwordsFrom
chosen
Indicates that two languages share loanwords that originate from the same source language.
-
E.
sharesUniverseWith
Indicates that two entities exist within the same fictional or narrative universe, implying shared continuity, setting, or canon.
- 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_69a88648cd44819093303206d96d76ad |
completed | March 4, 2026, 7:21 p.m. |
| NER | Named-entity recognition | batch_69abb32d35508190bf1c487dffbecaf0 |
completed | March 7, 2026, 5:10 a.m. |
| PD | Predicate disambiguation | batch_69abafdca6d8819083c66f3a29fd9fd1 |
completed | March 7, 2026, 4:55 a.m. |
Created at: March 4, 2026, 7:33 p.m.