Triple
T33027511
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | TYPE |
E845080
|
entity |
| Predicate | sentOver |
P175709
|
FINISHED |
| Object | control connection |
—
|
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: control connection | Statement: [TYPE, sentOver, control connection]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: sentOver Context triple: [TYPE, sentOver, control connection]
-
A.
sentAs
Indicates that one entity was transmitted, dispatched, or delivered in the form, role, or capacity of another (e.g., an item or message being sent as something specific).
-
B.
sentAfter
Indicates that one message or item was sent at a later time than another specified message or item.
-
C.
sentSon
Indicates that one entity caused or arranged for their son to be sent to another entity or location.
-
D.
sentOn
Indicates that one entity transmitted or dispatched something to another entity at a specific time or date.
-
E.
sentWhen
Indicates the time or temporal context at which a message, item, or communication was sent.
- 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_69f34950749c8190ae05cd27adb16d58 |
completed | April 30, 2026, 12:21 p.m. |
| NER | Named-entity recognition | batch_69f6d74b20a48190900dda1014cc13a8 |
completed | May 3, 2026, 5:04 a.m. |
| PD | Predicate disambiguation | batch_69f6d27120988190aacec621cf2bf0e8 |
completed | May 3, 2026, 4:43 a.m. |
| PDg | Predicate description generation | batch_69f6d6a482fc8190b526291cd99b8696 |
completed | May 3, 2026, 5:01 a.m. |
Created at: May 1, 2026, 1:23 a.m.