Triple
T31116008
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Zhenling Mausoleum |
E793089
|
entity |
| Predicate | hasPrimaryDeceased |
P201971
|
FINISHED |
| Object | Emperor Dezong 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 Dezong of Tang | Statement: [Zhenling Mausoleum, hasPrimaryDeceased, Emperor Dezong of Tang]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasPrimaryDeceased Context triple: [Zhenling Mausoleum, hasPrimaryDeceased, Emperor Dezong of Tang]
-
A.
hasDeceasedParent
Indicates that an entity has at least one parent who is no longer living.
-
B.
onceDeceased
Indicates that an entity was previously dead at some point in time, regardless of its current state.
-
C.
hasSubjectDeathEvent
Indicates that an entity is associated with an event representing the death of its subject.
-
D.
predeceasedBy
Indicates that the subject died before the referenced entity.
-
E.
spouseDateOfDeath
Indicates the date on which a person's spouse died.
- 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_69f224d0a7688190af3fe3e6e26d01ed |
completed | April 29, 2026, 3:33 p.m. |
| NER | Named-entity recognition | batch_6a003f6083608190a5deadc7291cf70e |
completed | May 10, 2026, 8:18 a.m. |
| PD | Predicate disambiguation | batch_6a003c935c40819085fdb255a52ba03b |
completed | May 10, 2026, 8:06 a.m. |
| PDg | Predicate description generation | batch_6a003f5fa0108190bea7f7b6b6ec6baf |
completed | May 10, 2026, 8:18 a.m. |
Created at: April 29, 2026, 9:04 p.m.