Triple
T32792593
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tianshou |
E838670
|
entity |
| Predicate | preImperialDynastyContext |
P175124
|
FINISHED |
| Object | Tang dynasty |
—
|
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: Tang dynasty | Statement: [Tianshou, preImperialDynastyContext, Tang dynasty]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: preImperialDynastyContext Context triple: [Tianshou, preImperialDynastyContext, Tang dynasty]
-
A.
preImperialContext
Indicates that the relationship or action occurs in, refers to, or is conditioned by a context that predates an imperial or empire-forming period.
-
B.
pre-imperialRole
Indicates that an entity held a particular role or position during a pre-imperial period, before the establishment of an empire or imperial rule.
-
C.
preImperialStatus
Indicates the status or condition an entity held prior to the establishment or onset of an imperial regime or imperial rule.
-
D.
preImperialName
Indicates the name an entity held before it became part of, or was incorporated into, an empire or imperial system.
-
E.
earlierDynasty
Indicates that one dynasty chronologically precedes another in historical succession.
- 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_69f3493c7f6881908edf2aa13631d1e0 |
completed | April 30, 2026, 12:21 p.m. |
| NER | Named-entity recognition | batch_69f6cee547108190ad3bc84297d8f516 |
completed | May 3, 2026, 4:28 a.m. |
| PD | Predicate disambiguation | batch_69f6cc1667a48190b42684f6ec22dae9 |
completed | May 3, 2026, 4:16 a.m. |
| PDg | Predicate description generation | batch_69f6ce6c76bc8190b865343d3f5810c9 |
completed | May 3, 2026, 4:26 a.m. |
Created at: May 1, 2026, 1:14 a.m.