Triple
T8019518
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Observatory |
E186702
|
entity |
| Predicate | levelOfInstitutionDocumented |
P50117
|
FINISHED |
| Object | public specialized high school |
—
|
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: public specialized high school | Statement: [The Observatory, levelOfInstitutionDocumented, public specialized high school]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: levelOfInstitutionDocumented Context triple: [The Observatory, levelOfInstitutionDocumented, public specialized high school]
-
A.
institutionalLevel
chosen
Indicates the hierarchical or organizational tier at which an institution or its component operates or is classified.
-
B.
establishedInstitution
Indicates that an entity founded, created, or formally set up an institution or organization.
-
C.
typeOfInstitution
Indicates the specific kind or category of institution that an entity belongs to or is classified as.
-
D.
inInstitution
Indicates that an entity is located within, belongs to, or is formally associated with a particular institution.
-
E.
taughtAtLevel
Indicates that an entity provided instruction or teaching at a specified level of education, difficulty, or proficiency.
- 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_69ca82ac7fc081909b1398cf025423af |
completed | March 30, 2026, 2:03 p.m. |
| NER | Named-entity recognition | batch_69cb3e8bc90081909f6f5878e6f1f241 |
completed | March 31, 2026, 3:24 a.m. |
| PD | Predicate disambiguation | batch_69cb049253d08190bafcecfde493ab8b |
completed | March 30, 2026, 11:17 p.m. |
Created at: March 30, 2026, 5:20 p.m.