Triple
T3547993
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Chenghua Emperor |
E75041
|
entity |
| Predicate | courtCharacteristic |
P50505
|
FINISHED |
| Object | dominance of palace eunuchs |
—
|
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: dominance of palace eunuchs | Statement: [Chenghua Emperor, courtCharacteristic, dominance of palace eunuchs]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: courtCharacteristic Context triple: [Chenghua Emperor, courtCharacteristic, dominance of palace eunuchs]
-
A.
legalSystemFeature
Indicates a characteristic, rule, or structural element that forms part of a particular legal system.
-
B.
courtContext
Indicates the legal or judicial setting, circumstances, or framework within which a court-related action or relationship takes place.
-
C.
courtOfficial
Indicates that an entity serves in an official capacity within a court, holding an authorized role in judicial or legal proceedings.
-
D.
courtRole
Indicates the specific capacity or position an entity holds within a court proceeding or judicial context.
-
E.
recognizesCourt
Indicates that one legal authority formally accepts the legitimacy or jurisdiction of a particular court.
- F. None of above. chosen
Provenance (4 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_69ad85d33c6c819081d5ac1df13b5680 |
completed | March 8, 2026, 2:21 p.m. |
| NER | Named-entity recognition | batch_69adbfd0eb6081908f1380db4cfade87 |
completed | March 8, 2026, 6:28 p.m. |
| PD | Predicate disambiguation | batch_69adb83270ac819083967db0570167d2 |
completed | March 8, 2026, 5:56 p.m. |
| PDg | Predicate description generation | batch_69adba25c66c81909a05a97327828c41 |
completed | March 8, 2026, 6:04 p.m. |
Created at: March 8, 2026, 3:20 p.m.