Triple
T23166125
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Yuan Dadu |
E578714
|
entity |
| Predicate | modernRemnantsType |
P57740
|
FINISHED |
| Object | archaeological remains |
—
|
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: archaeological remains | Statement: [Yuan Dadu, modernRemnantsType, archaeological remains]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: modernRemnantsType Context triple: [Yuan Dadu, modernRemnantsType, archaeological remains]
-
A.
remnantType
chosen
Indicates the specific kind or category of remnant that results from or is associated with an entity or process.
-
B.
modernBase
Indicates that one entity serves as the contemporary or current foundational basis or reference point for another entity.
-
C.
remnants
Indicates that parts or traces of something remain after the main portion has been removed, used, or destroyed.
-
D.
modernVariation
Indicates that one entity is a contemporary or updated version, adaptation, or reinterpretation of another.
-
E.
modernDimension
Indicates a relationship where something is characterized by or associated with contemporary or current-era qualities, styles, or conditions.
- 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_69e245fc75348190a0288401044c8af8 |
completed | April 17, 2026, 2:38 p.m. |
| NER | Named-entity recognition | batch_69f18f2c923c81908b58811fffdcf932 |
completed | April 29, 2026, 4:55 a.m. |
| PD | Predicate disambiguation | batch_69ef89ff76808190808ee4ad9dea776b |
completed | April 27, 2026, 4:08 p.m. |
Created at: April 17, 2026, 4:03 p.m.