Triple
T9640691
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Emperor Yizong of Tang |
E233055
|
entity |
| Predicate | courtIssue |
P89399
|
FINISHED |
| Object | corruption among officials |
—
|
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: corruption among officials | Statement: [Emperor Yizong of Tang, courtIssue, corruption among officials]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: courtIssue Context triple: [Emperor Yizong of Tang, courtIssue, corruption among officials]
-
A.
courtFeatured
Indicates that a particular court prominently presented, highlighted, or showcased a given entity (such as a case, event, or person) in an official or notable context.
-
B.
courtReview
Indicates that a court formally examines a decision, action, or case to determine its legality, correctness, or appropriateness.
-
C.
courtContext
Indicates the legal or judicial setting, circumstances, or framework within which a court-related action or relationship takes place.
-
D.
courtNumber
Indicates the specific numbered court (e.g., field, room, or venue) assigned or associated with an event, case, or match.
-
E.
courtTitle
Indicates the official judicial position or title held by a person within a court system.
- 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_69ca848a5a908190aad251f4137b0c3a |
completed | March 30, 2026, 2:11 p.m. |
| NER | Named-entity recognition | batch_69cd9b552a1c81909a1fab347110eeb1 |
completed | April 1, 2026, 10:25 p.m. |
| PD | Predicate disambiguation | batch_69ccd5b0263081908cf6df3eb07d71b0 |
completed | April 1, 2026, 8:22 a.m. |
| PDg | Predicate description generation | batch_69ccd93fc45c8190a823305e461e581d |
completed | April 1, 2026, 8:37 a.m. |
Created at: March 30, 2026, 8:12 p.m.