Triple
T3173945
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Fannie Mae |
E66416
|
entity |
| Predicate | charter |
P19150
|
FINISHED |
| Object | federally chartered |
—
|
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: federally chartered | Statement: [Fannie Mae, charter, federally chartered]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: charter Context triple: [Fannie Mae, charter, federally chartered]
-
A.
charterRevised
Indicates that an existing charter has been modified or updated from its previous version.
-
B.
charterFeature
Indicates that an entity (such as a service, product, or offering) includes or provides a specific feature as part of a charter or special arrangement.
-
C.
charterType
chosen
Indicates the specific category or kind of charter under which an entity, agreement, or operation is formally established or governed.
-
D.
charterName
Indicates the official name or title assigned in a charter that defines or authorizes an entity or arrangement.
-
E.
charterConfirmedBy
Indicates that an official charter has been formally approved or validated by a specified authority or 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_69ad8586a34c8190944c63ec11a8de1a |
completed | March 8, 2026, 2:19 p.m. |
| NER | Named-entity recognition | batch_69ada670c800819098937783e2b05c7a |
completed | March 8, 2026, 4:40 p.m. |
| PD | Predicate disambiguation | batch_69ad9e0076b4819094628f1ad10b8f68 |
completed | March 8, 2026, 4:04 p.m. |
Created at: March 8, 2026, 3:06 p.m.