Triple
T28075818
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Empty Fort Strategy |
E709538
|
entity |
| Predicate | opponentDeceived |
P7322
|
FINISHED |
| Object | Sima Yi |
—
|
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: Sima Yi | Statement: [Empty Fort Strategy, opponentDeceived, Sima Yi]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: opponentDeceived Context triple: [Empty Fort Strategy, opponentDeceived, Sima Yi]
-
A.
tricked
chosen
Indicates that one entity intentionally deceived another into believing something false or acting under a false impression.
-
B.
usedMeansOfDeception
Indicates that one entity employed a particular method or tool specifically to deceive another entity.
-
C.
oftenDeceives
Indicates that one entity frequently engages in deceptive behavior toward another entity.
-
D.
typeOfDeception
Indicates the specific kind or category of deceptive act that one entity employs toward another or in a given context.
-
E.
aidedOpponent
Indicates that one entity provided help or support to another entity who is considered an opponent or adversary.
- 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_69ef9b6f8078819098b741274cd1a2ee |
completed | April 27, 2026, 5:22 p.m. |
| NER | Named-entity recognition | batch_69f64dbbaefc8190952b8320bf4397d8 |
completed | May 2, 2026, 7:17 p.m. |
| PD | Predicate disambiguation | batch_69f64cacd2c08190aed8a1761d0da679 |
completed | May 2, 2026, 7:12 p.m. |
Created at: April 27, 2026, 8:48 p.m.