Triple
T3039378
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jin (Chinese surname associated with Kaifeng Jews) |
E83087
|
entity |
| Predicate | sharesCategoryWith |
P5696
|
FINISHED |
| Object | other Chinese surnames adopted by Kaifeng Jews |
—
|
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: other Chinese surnames adopted by Kaifeng Jews | Statement: [Jin (Chinese surname associated with Kaifeng Jews), sharesCategoryWith, other Chinese surnames adopted by Kaifeng Jews]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: sharesCategoryWith Context triple: [Jin (Chinese surname associated with Kaifeng Jews), sharesCategoryWith, other Chinese surnames adopted by Kaifeng Jews]
-
A.
sharesUniverseWith
Indicates that two entities exist within the same fictional or narrative universe, implying shared continuity, setting, or canon.
-
B.
sharesFeatureWith
chosen
Indicates that two entities have at least one common attribute, property, or characteristic in common.
-
C.
sharesCommunityWith
Indicates that two entities belong to or participate in the same community or communal group.
-
D.
sharesModuleWith
Indicates that two entities are associated with or participate in at least one common module.
-
E.
sharesRouteWith
Indicates that two entities follow or operate along the same or overlapping route.
- 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_69ad8b2298908190a7cb4e9bdbf064d0 |
completed | March 8, 2026, 2:43 p.m. |
| NER | Named-entity recognition | batch_69ad9b2fa52c8190a7860f762d5232ab |
completed | March 8, 2026, 3:52 p.m. |
| PD | Predicate disambiguation | batch_69ad961fc62c819087c4c3a44b00847d |
completed | March 8, 2026, 3:30 p.m. |
Created at: March 8, 2026, 3:01 p.m.