Triple
T27927447
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lian Po |
E707876
|
entity |
| Predicate | roleInBattleOfChangping |
P28183
|
FINISHED |
| Object | commander of Zhao defensive forces |
—
|
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: commander of Zhao defensive forces | Statement: [Lian Po, roleInBattleOfChangping, commander of Zhao defensive forces]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: roleInBattleOfChangping Context triple: [Lian Po, roleInBattleOfChangping, commander of Zhao defensive forces]
-
A.
opponentStateAtBattleOfChangping
Indicates that the referenced entity was in an opposing position or role during the Battle of Changping.
-
B.
notableBattleRole
chosen
Indicates the specific role or function an entity played in a notable or historically significant battle.
-
C.
sideInBattleOfYiling
Indicates that an entity participated as a side or faction in the Battle of Yiling.
-
D.
roleInTrojanWar
Indicates the specific function, position, or part an entity played in the events of the Trojan War.
-
E.
ChineseCommander
Indicates that an individual holds a commander role within a Chinese military or armed forces context.
- 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_69ef96bbf2c48190a9d0e0291457aab6 |
completed | April 27, 2026, 5:02 p.m. |
| NER | Named-entity recognition | batch_69fd82ed2a4c81908bd7797fbd2e3d08 |
completed | May 8, 2026, 6:30 a.m. |
| PD | Predicate disambiguation | batch_69fd814cc10481908e4f8123d35a5d0c |
completed | May 8, 2026, 6:23 a.m. |
Created at: April 27, 2026, 7:01 p.m.