Triple
T27959006
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tian Wen |
E704528
|
entity |
| Predicate | questionAddressee |
P92617
|
FINISHED |
| Object | Heaven |
—
|
NE NERFINISHED |
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: Heaven | Statement: [Tian Wen, questionAddressee, Heaven]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: questionAddressee Context triple: [Tian Wen, questionAddressee, Heaven]
-
A.
addresseeOf
chosen
Indicates that one entity is the intended recipient or target audience of a communication, message, or expression from another entity.
-
B.
addresseeType
Indicates the role or category of the entity that is the intended recipient or target of a communication or message.
-
C.
addresseeDescription
Indicates that one entity provides a descriptive characterization or identifying information about the addressee of a communication or message.
-
D.
normAddressee
Indicates that a particular entity is the socially or conventionally appropriate recipient or target of an utterance, message, or communicative act.
-
E.
addressedBy
Indicates that something (such as an issue, request, or item) is handled, dealt with, or responded to by a particular agent 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_69ef841061e48190b5570f9562f7434d |
completed | April 27, 2026, 3:43 p.m. |
| NER | Named-entity recognition | batch_69f63fd6c68481908c542aa03e297b9c |
completed | May 2, 2026, 6:17 p.m. |
| PD | Predicate disambiguation | batch_69f63c6895f0819088655277e45859a8 |
completed | May 2, 2026, 6:03 p.m. |
Created at: April 27, 2026, 7:30 p.m.