Triple
T29409615
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jiang Wei |
E745857
|
entity |
| Predicate | laterDefectedTo |
P12199
|
FINISHED |
| Object | Shu Han |
—
|
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: Shu Han | Statement: [Jiang Wei, laterDefectedTo, Shu Han]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: laterDefectedTo Context triple: [Jiang Wei, laterDefectedTo, Shu Han]
-
A.
defectedTo
chosen
Indicates that an entity abandoned its original side, group, or allegiance and joined or gave support to another, typically opposing, side.
-
B.
attemptedDefectionTo
Indicates an action where one party tried, but may not have succeeded, to leave or abandon their current side, group, or allegiance in order to join another specified party.
-
C.
timeOfDefection
Indicates the specific time at which an entity defected or switched allegiance from one side, group, or affiliation to another.
-
D.
defectedMembers
Indicates members who have abandoned or switched allegiance from one group, organization, or side to another.
-
E.
afterDefectionTitle
Indicates that a title or designation is assigned to an entity specifically after it has defected from a previous affiliation or allegiance.
- 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_69f0a79eb7d081908c67197a5f347e68 |
completed | April 28, 2026, 12:27 p.m. |
| NER | Named-entity recognition | batch_69fe68a4b67881909ca1d9f276f922e0 |
completed | May 8, 2026, 10:50 p.m. |
| PD | Predicate disambiguation | batch_69fe680234c88190b01f953987b74972 |
completed | May 8, 2026, 10:47 p.m. |
Created at: April 28, 2026, 2:56 p.m.