Triple
T30648966
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Biblioteca Central |
E780201
|
entity |
| Predicate | equivalentLabelInEnglish |
P3437
|
FINISHED |
| Object | Central Library |
—
|
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: Central Library | Statement: [Biblioteca Central, equivalentLabelInEnglish, Central Library]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: equivalentLabelInEnglish Context triple: [Biblioteca Central, equivalentLabelInEnglish, Central Library]
-
A.
equivalentGivenNameInEnglish
Indicates that two given names are equivalent in meaning or usage when expressed in English.
-
B.
equivalentIn
Indicates that two entities are considered logically or functionally the same in meaning, status, or effect within a given context.
-
C.
languageEquivalent
Indicates that two linguistic expressions convey the same meaning or function across different languages or language varieties.
-
D.
equivalentEpithetLanguage
Indicates that two epithets are expressed in different languages but convey the same meaning or designation.
-
E.
hasEnglishName
chosen
Indicates that an entity is associated with a name expressed in the English language.
- 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_69f224a5d2b481908a6853cd0138e2d7 |
completed | April 29, 2026, 3:32 p.m. |
| NER | Named-entity recognition | batch_69f69dfdda708190be290c7bec205445 |
completed | May 3, 2026, 12:59 a.m. |
| PD | Predicate disambiguation | batch_69f69d1a37e081908d1d86b90ff502bd |
completed | May 3, 2026, 12:55 a.m. |
Created at: April 29, 2026, 8:30 p.m.