Triple
T32458170
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Emperor Wu of Han |
E829486
|
entity |
| Predicate | orderedMissionOf |
P122387
|
FINISHED |
| Object | Zhang Qian |
—
|
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: Zhang Qian | Statement: [Emperor Wu of Han, orderedMissionOf, Zhang Qian]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: orderedMissionOf Context triple: [Emperor Wu of Han, orderedMissionOf, Zhang Qian]
-
A.
missionOrder
Indicates that one mission is ordered, sequenced, or prioritized relative to another within an overall mission plan.
-
B.
commandedMission
chosen
Indicates that one entity served as the commanding leader or officer in charge of a particular mission carried out by another entity.
-
C.
assignedMission
Indicates that an entity has been given a specific mission or task to carry out.
-
D.
publicMission
Indicates that an entity carries out a mission or activity intended for the general public or serving public interests.
-
E.
hasMissionTo
Indicates that an entity is assigned or dedicated to carrying out a specific mission, task, or purpose related to another entity or objective.
- 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_69f3491df9288190afc0b23b1d6e72ce |
completed | April 30, 2026, 12:20 p.m. |
| NER | Named-entity recognition | batch_69f71f8ee0688190bd025f27993452d3 |
completed | May 3, 2026, 10:12 a.m. |
| PD | Predicate disambiguation | batch_69f71cc405c08190863565609a4c8499 |
completed | May 3, 2026, 10 a.m. |
Created at: May 1, 2026, 12:56 a.m.