Triple
T27141748
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Government and Binding |
E681832
|
entity |
| Predicate | assumesLevel |
P162511
|
FINISHED |
| Object | deep structure |
—
|
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: deep structure | Statement: [Government and Binding, assumesLevel, deep structure]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: assumesLevel Context triple: [Government and Binding, assumesLevel, deep structure]
-
A.
assumes
Indicates that one entity takes on, accepts, or presumes a role, responsibility, state, or fact regarding another entity or situation.
-
B.
assumesAccessTo
Indicates that one entity presupposes or takes for granted that it has access to another entity, resource, or piece of information.
-
C.
approvalLevel
Indicates the degree or extent to which one entity formally accepts, endorses, or agrees with another entity or action.
-
D.
assessmentLevel
Indicates the degree, rating, or intensity assigned to an evaluation or judgment of something.
-
E.
hasLevel
Indicates that an entity possesses or is associated with a particular degree, rank, or stage within an ordered scale or hierarchy.
- 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_69eefacca3888190b67238d380e8f28b |
completed | April 27, 2026, 5:57 a.m. |
| NER | Named-entity recognition | batch_69f62b9e5ba88190a3c0d46edec7afe7 |
completed | May 2, 2026, 4:51 p.m. |
| PD | Predicate disambiguation | batch_69f623a91b9c8190b2e2fdbc55cb89b6 |
completed | May 2, 2026, 4:17 p.m. |
| PDg | Predicate description generation | batch_69f625402d808190be8279d895d2b27f |
completed | May 2, 2026, 4:24 p.m. |
Created at: April 27, 2026, 9:09 a.m.