Triple
T2896377
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Foreign Service Institute |
E63948
|
entity |
| Predicate | languageTrainingCapacity |
P14732
|
FINISHED |
| Object | over 70 languages |
—
|
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: over 70 languages | Statement: [Foreign Service Institute, languageTrainingCapacity, over 70 languages]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: languageTrainingCapacity Context triple: [Foreign Service Institute, languageTrainingCapacity, over 70 languages]
-
A.
languageCapacity
Indicates the extent to which an entity is able to understand, produce, or otherwise use language.
-
B.
estimatedNumberOfLanguages
chosen
Indicates the approximate count of distinct languages associated with an entity, typically based on estimation rather than an exact measurement.
-
C.
trainingDomain
Indicates that an entity is associated with or operates within a particular field, area, or domain of training.
-
D.
providesTrainingFor
Indicates that one entity delivers or conducts training activities intended to develop the skills or knowledge of another entity.
-
E.
hasNumberOfLessons
Indicates the specific count of lessons associated with an entity.
- 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_69ab4c45822c8190830c5f2bb97bcfd0 |
completed | March 6, 2026, 9:51 p.m. |
| NER | Named-entity recognition | batch_69abe08c85c48190bd8c0f6680fca0c8 |
completed | March 7, 2026, 8:23 a.m. |
| PD | Predicate disambiguation | batch_69abdd17bcdc8190aa47274a50ba4ad4 |
completed | March 7, 2026, 8:08 a.m. |
Created at: March 6, 2026, 10:08 p.m.