Triple
T35130565
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Embassy of the Philippines in Jakarta |
E1014422
|
entity |
| Predicate | hostCountryLanguageUsed |
P149047
|
FINISHED |
| Object | Indonesian |
—
|
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: Indonesian | Statement: [Embassy of the Philippines in Jakarta, hostCountryLanguageUsed, Indonesian]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hostCountryLanguageUsed Context triple: [Embassy of the Philippines in Jakarta, hostCountryLanguageUsed, Indonesian]
-
A.
hostCountryLanguageContext
Indicates the linguistic environment or language norms present in the country where an entity is hosted or operating.
-
B.
languageOfSurroundingCountry
chosen
Indicates that a language is the primary or commonly used language in the country surrounding a given place or region.
-
C.
primaryLanguageCountry
Indicates that a given language is the main or officially predominant language used within a particular country.
-
D.
governingCountryLanguage
Indicates that a particular language is officially used or recognized by the governing authorities of a given country.
-
E.
countryOfLanguage
Indicates that a particular language is officially or predominantly used within a specified country.
- 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_69f76dd9c1848190af70d4882a2c1ad7 |
completed | May 3, 2026, 3:46 p.m. |
| NER | Named-entity recognition | batch_69f78c680d208190b822194d4dd4cd62 |
completed | May 3, 2026, 5:56 p.m. |
| PD | Predicate disambiguation | batch_69f78b9106008190930b3b3675b737d6 |
completed | May 3, 2026, 5:53 p.m. |
Created at: May 3, 2026, 4:02 p.m.