Triple
T30444465
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Chinatown, Ho Chi Minh City |
E774536
|
entity |
| Predicate | primaryReligions |
P81268
|
FINISHED |
| Object | Chinese folk religion |
—
|
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: Chinese folk religion | Statement: [Chinatown, Ho Chi Minh City, primaryReligions, Chinese folk religion]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: primaryReligions Context triple: [Chinatown, Ho Chi Minh City, primaryReligions, Chinese folk religion]
-
A.
dominantReligion
Indicates the religion that holds primary or majority status within a given group, region, or entity.
-
B.
laterReligionDominant
Indicates that a religion adopted or followed at a later time becomes the dominant or primary religion in the relevant context or entity.
-
C.
officialReligion
Indicates that a particular religion is formally recognized and designated as the official or state religion of an entity (such as a country or region).
-
D.
majorReligionCanBe
chosen
Indicates that an entity can have a particular major religion as one of its possible primary religious affiliations.
-
E.
orderReligion
Indicates that one entity prescribes, organizes, or regulates the religious practices, beliefs, or structure of 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_69f22493ef9c8190ae8c2afcb7f994c8 |
completed | April 29, 2026, 3:32 p.m. |
| NER | Named-entity recognition | batch_6a022c5269888190944314074aedfe73 |
completed | May 11, 2026, 7:21 p.m. |
| PD | Predicate disambiguation | batch_6a02286020308190b238183f7ba2065f |
completed | May 11, 2026, 7:05 p.m. |
Created at: April 29, 2026, 8:08 p.m.