Triple
T32368434
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tianyou |
E827062
|
entity |
| Predicate | reignTitleOf |
P168622
|
FINISHED |
| Object | Emperor Zhaozong of Tang |
—
|
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: Emperor Zhaozong of Tang | Statement: [Tianyou, reignTitleOf, Emperor Zhaozong of Tang]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: reignTitleOf Context triple: [Tianyou, reignTitleOf, Emperor Zhaozong of Tang]
-
A.
reignAs
Indicates that an entity holds and exercises ruling authority or sovereignty over a domain or people for a period of time.
-
B.
reignTo
Indicates that one entity exercises ruling authority or governance over another entity or domain during a particular period.
-
C.
reignWith
Indicates that one entity rules or holds sovereign authority jointly alongside another entity.
-
D.
regentTitle
Indicates the official title held by a person serving as regent (i.e., governing on behalf of another, such as a monarch or minor).
-
E.
correspondsToReignTitleHolder
chosen
Indicates that a given reign or period of rule is associated with, and held by, a specific title holder.
- 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_69f349166d548190887b412fe908e2f4 |
completed | April 30, 2026, 12:20 p.m. |
| NER | Named-entity recognition | batch_69f7aa699d68819081ed363931894ab3 |
completed | May 3, 2026, 8:04 p.m. |
| PD | Predicate disambiguation | batch_69f7a8cec6d48190bebfa884b2f938c0 |
completed | May 3, 2026, 7:58 p.m. |
Created at: May 1, 2026, 12:50 a.m.