Triple
T27959804
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sun family of Eastern Wu |
E704549
|
entity |
| Predicate | stateFoundedYear |
P13772
|
FINISHED |
| Object | 222 |
—
|
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: 222 | Statement: [Sun family of Eastern Wu, stateFoundedYear, 222]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: stateFoundedYear Context triple: [Sun family of Eastern Wu, stateFoundedYear, 222]
-
A.
stateFoundedIn
chosen
Indicates that a particular state was established or came into existence in a specified year or time period.
-
B.
stateFounded
Indicates that a particular state was established or created at a specific time or by a specific founding event or agent.
-
C.
stateTypeFounded
Indicates that a particular type or category of state was established or came into existence at a certain point or by a certain founding event.
-
D.
statehoodYear
Indicates the year in which an entity officially became a recognized state or attained statehood status.
-
E.
coFoundedInYear
Indicates that two or more entities jointly founded something (such as an organization or company) in a specified year.
- 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_69f7886be6d8819095ec62e4f2cee858 |
completed | May 3, 2026, 5:39 p.m. |
| PD | Predicate disambiguation | batch_69f7841440f48190b4346c08855951d2 |
completed | May 3, 2026, 5:21 p.m. |
Created at: April 27, 2026, 7:30 p.m.