Triple
T21967272
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Four Supplements |
E542490
|
entity |
| Predicate | canonRelation |
P109879
|
FINISHED |
| Object | appendix to main Daozang |
—
|
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: appendix to main Daozang | Statement: [Four Supplements, canonRelation, appendix to main Daozang]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: canonRelation Context triple: [Four Supplements, canonRelation, appendix to main Daozang]
-
A.
subjectRelation
Indicates that one entity stands in a specified relational role or connection to another entity.
-
B.
allyRelation
Indicates a cooperative, supportive relationship in which the entities act as allies toward shared or aligned goals.
-
C.
unitRelation
Indicates a relationship between units, such as how one unit is associated with, derived from, or converted to another.
-
D.
seriesRelation
chosen
Indicates a relationship where one entity is part of, follows from, or is otherwise connected to another within an ordered series or sequence.
-
E.
titleRelation
Indicates a relationship where one entity serves as the title, designation, or formal name associated with another entity.
- 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_69e0c47fab1081908dc74a6545dbb051 |
completed | April 16, 2026, 11:14 a.m. |
| NER | Named-entity recognition | batch_69f1245b821c8190816058c2a07707a3 |
completed | April 28, 2026, 9:19 p.m. |
| PD | Predicate disambiguation | batch_69e6f601f2188190893bcdde0cf58ad6 |
completed | April 21, 2026, 3:58 a.m. |
Created at: April 16, 2026, 8:01 p.m.