Triple
T26876040
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Illinois lies generally northwest of Kentucky |
E676750
|
entity |
| Predicate | hasAdverb |
P171412
|
FINISHED |
| Object | generally |
—
|
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: generally | Statement: [Illinois lies generally northwest of Kentucky, hasAdverb, generally]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasAdverb Context triple: [Illinois lies generally northwest of Kentucky, hasAdverb, generally]
-
A.
hasAdverbEnding
Indicates that something (typically a word) ends with a suffix or form characteristic of an adverb.
-
B.
hasAdjectiveForm
Indicates that one term is the adjective form derived from another related term (such as a noun or verb).
-
C.
hasAdjectiveEnding
Indicates that something possesses or is marked by a particular adjective-like ending or suffix.
-
D.
hasVerbAspect
Indicates that a verb or verbal expression is associated with a particular grammatical aspect (such as perfective, imperfective, or progressive) describing the temporal structure of the action or state.
-
E.
hasParticiple
Indicates that one entity is associated with the participle form (verbal adjective or non-finite verb form) of another entity.
- 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_69eee9bb44988190b6e11652d028bc59 |
completed | April 27, 2026, 4:44 a.m. |
| NER | Named-entity recognition | batch_69f69f80b62c8190bf2af2be0d3a7df8 |
completed | May 3, 2026, 1:06 a.m. |
| PD | Predicate disambiguation | batch_69f69d17e8d48190b30bcc2f4bd81eb2 |
completed | May 3, 2026, 12:55 a.m. |
| PDg | Predicate description generation | batch_69f69edae2448190925ce701c8792c52 |
completed | May 3, 2026, 1:03 a.m. |
Created at: April 27, 2026, 5:36 a.m.