Triple
T4327391
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Old Lady |
E96664
|
entity |
| Predicate | refersToInstitutionType |
P29027
|
FINISHED |
| Object | central bank |
—
|
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: central bank | Statement: [Old Lady, refersToInstitutionType, central bank]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: refersToInstitutionType Context triple: [Old Lady, refersToInstitutionType, central bank]
-
A.
associatedInstitutionType
chosen
Indicates the type or category of institution with which an entity is associated.
-
B.
usedByInstitutionType
Indicates that something (such as a resource, tool, or service) is utilized or employed by a particular type or category of institution.
-
C.
governsInstitutionType
Indicates that an entity has authoritative control or regulatory oversight over a particular type or category of institution.
-
D.
recognizedAsInstitutionBy
Indicates that an entity is acknowledged or accepted as an institution by a specified recognizing party.
-
E.
typeOfInstitution
Indicates the specific kind or category of institution that an entity belongs to or is classified as.
- 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_69b34542fd908190b11b08faad8decfd |
completed | March 12, 2026, 10:59 p.m. |
| NER | Named-entity recognition | batch_69b35131f11881909e2d5415a70d5785 |
completed | March 12, 2026, 11:50 p.m. |
| PD | Predicate disambiguation | batch_69b34f4e13fc8190a42c519f37959d27 |
completed | March 12, 2026, 11:42 p.m. |
Created at: March 12, 2026, 11:13 p.m.