Triple
T23408994
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Waishengren |
E560012
|
entity |
| Predicate | identityTrend |
P39078
|
FINISHED |
| Object | increasing intermarriage with benshengren |
—
|
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: increasing intermarriage with benshengren | Statement: [Waishengren, identityTrend, increasing intermarriage with benshengren]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: identityTrend Context triple: [Waishengren, identityTrend, increasing intermarriage with benshengren]
-
A.
trends
chosen
Indicates that one entity exhibits a general direction of change or development over time in relation to another reference or context.
-
B.
intellectualTrend
Indicates a relationship where an idea, movement, or way of thinking is recognized as an intellectual trend influencing thought or discourse.
-
C.
identityFeatures
Indicates that certain characteristics or attributes are used to define, distinguish, or uniquely identify an entity.
-
D.
identityShapedBy
Indicates that one entity’s identity is influenced, formed, or defined by another entity or factor.
-
E.
identityCategory
Indicates that an entity belongs to, or is classified under, a particular identity-based category or group.
- 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_69e2454b3a5881909c64773dc8a5d289 |
completed | April 17, 2026, 2:35 p.m. |
| NER | Named-entity recognition | batch_69f1a50fff10819094e71fb0c11b7d95 |
completed | April 29, 2026, 6:28 a.m. |
| PD | Predicate disambiguation | batch_69f061ed34288190a2e5e8cae03b0095 |
completed | April 28, 2026, 7:29 a.m. |
Created at: April 17, 2026, 5:38 p.m.