Triple
T27323710
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Shang Xiaoyun |
E689580
|
entity |
| Predicate | peerWith |
P6215
|
FINISHED |
| Object | Mei Lanfang |
—
|
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: Mei Lanfang | Statement: [Shang Xiaoyun, peerWith, Mei Lanfang]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: peerWith Context triple: [Shang Xiaoyun, peerWith, Mei Lanfang]
-
A.
peerOf
chosen
Indicates that two entities hold equivalent or comparable status, role, or standing within the same context or system.
-
B.
peerFestival
Indicates that two festivals are considered peers, sharing a comparable status, scale, or role within a given context.
-
C.
partnerInOrganizationWith
Indicates that two entities are associated as partners within the same organization or organizational context.
-
D.
partnerInRuleWith
Indicates that two or more entities jointly participate as partners in establishing, enforcing, or being governed by the same rule or regulatory framework.
-
E.
coMemberWith
Indicates that two or more entities share membership in the same group, organization, or collective.
- 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_69ef355d4cb08190ab032c0a2e7d3753 |
completed | April 27, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69f627ec3fd081909153e7d281fd7214 |
completed | May 2, 2026, 4:35 p.m. |
| PD | Predicate disambiguation | batch_69f620e4b1c88190a17940251abc68fd |
completed | May 2, 2026, 4:05 p.m. |
Created at: April 27, 2026, 11:34 a.m.