Triple
T1175
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Washington, D.C. |
E23
|
entity |
| Predicate | hasOfficialLanguagePolicy |
P187
|
FINISHED |
| Object | no official language at federal level |
—
|
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: no official language at federal level | Statement: [Washington, D.C., hasOfficialLanguagePolicy, no official language at federal level]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasOfficialLanguagePolicy Context triple: [Washington, D.C., hasOfficialLanguagePolicy, no official language at federal level]
-
A.
primaryLanguageOfInstruction
Indicates the language that is mainly used as the medium of teaching or instruction for a given educational context.
-
B.
languageOfWorkOrName
Indicates the language in which a work is created or a name is expressed.
-
C.
officialName
Indicates the formally recognized name assigned to an entity by an authoritative body or source.
-
D.
countryOfCitizenship
Indicates the country in which a person or entity holds legal citizenship.
-
E.
admissionPolicy
Indicates the rules or criteria governing whether and how entities are allowed to be admitted or granted access.
- F. None of above. chosen
Provenance (4 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_69a22a285828819081a58308fb963df1 |
completed | Feb. 27, 2026, 11:35 p.m. |
| NER | Named-entity recognition | batch_69a23211f05c8190b8deb03a8540d84d |
completed | Feb. 28, 2026, 12:08 a.m. |
| PD | Predicate disambiguation | batch_69a230c2c48481908beb1db3cc9768aa |
completed | Feb. 28, 2026, 12:03 a.m. |
| PDg | Predicate description generation | batch_69a23211181c81909c2db8796d2aded4 |
completed | Feb. 28, 2026, 12:08 a.m. |
Created at: Feb. 27, 2026, 11:36 p.m.