Triple
T35511893
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Upendi |
E1026304
|
entity |
| Predicate | basedOnLanguageWord |
P140684
|
FINISHED |
| Object | Swahili word "upendo" |
—
|
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: Swahili word "upendo" | Statement: [Upendi, basedOnLanguageWord, Swahili word "upendo"]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: basedOnLanguageWord Context triple: [Upendi, basedOnLanguageWord, Swahili word "upendo"]
-
A.
basedOnWord
chosen
Indicates that one element is derived from, formed from, or directly influenced by a particular word.
-
B.
basedOnLanguagePhrase
Indicates that something is derived from, informed by, or constructed using a specific phrase in a particular natural language.
-
C.
basedOnPhrase
Indicates that something is derived from, inspired by, or constructed using a particular phrase as its source or foundation.
-
D.
languageOfWord
Indicates that a particular language is the one in which a given word is expressed or defined.
-
E.
hasLanguageOn
Indicates that an entity uses or is associated with a particular language in a specific context, medium, or location.
- 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_69f76dfd61208190b93ec6dc439cab41 |
completed | May 3, 2026, 3:47 p.m. |
| NER | Named-entity recognition | batch_69ff2636e2bc8190bba91eff91431c6e |
completed | May 9, 2026, 12:19 p.m. |
| PD | Predicate disambiguation | batch_69ff25c65be48190868480d94e1c4e89 |
completed | May 9, 2026, 12:17 p.m. |
Created at: May 3, 2026, 4:04 p.m.