Triple
T19382970
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Moldova at the Olympic Games |
E484858
|
entity |
| Predicate | languageOfDelegation |
P33549
|
FINISHED |
| Object | Romanian |
—
|
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: Romanian | Statement: [Moldova at the Olympic Games, languageOfDelegation, Romanian]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: languageOfDelegation Context triple: [Moldova at the Olympic Games, languageOfDelegation, Romanian]
-
A.
languageOfCommunications
chosen
Indicates that a specified language is used as the medium for communications associated with an entity or interaction.
-
B.
languageOfNegotiation
Indicates that a specified language is used as the medium of communication during a negotiation between parties.
-
C.
eligibleLanguage
Indicates that a particular language satisfies the required conditions to be considered valid or allowed in a given context.
-
D.
languageAgency
Indicates that an entity (such as a person or organization) has the capacity or authority to use, manage, or act through a particular language in performing actions or making decisions.
-
E.
languageOfExpression
Indicates that a particular language is used as the medium or form in which an expression (such as a text, utterance, or work) is realized.
- 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_69d8e8d460d88190abf0591c5c9d2b0c |
completed | April 10, 2026, 12:11 p.m. |
| NER | Named-entity recognition | batch_69e61a614cf88190b561eafaa350ce19 |
completed | April 20, 2026, 12:21 p.m. |
| PD | Predicate disambiguation | batch_69e4fd602f008190aa9bc76ae17e4ce1 |
completed | April 19, 2026, 4:05 p.m. |
Created at: April 10, 2026, 1:35 p.m.