Triple
T32847951
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dulong people |
E840154
|
entity |
| Predicate | historicalCustom |
P200920
|
FINISHED |
| Object | women’s facial tattooing |
—
|
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: women’s facial tattooing | Statement: [Dulong people, historicalCustom, women’s facial tattooing]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: historicalCustom Context triple: [Dulong people, historicalCustom, women’s facial tattooing]
-
A.
historicalType
Indicates that one entity classifies or characterizes another in terms of its role, status, or category within a historical context.
-
B.
historicalPattern
Indicates a recurring relationship or sequence of events between entities that has been observed over time.
-
C.
historicalFormat
Indicates that something is presented or recorded in a format that was used in the past, reflecting its historical or legacy form.
-
D.
historicalFunction
Indicates the role, purpose, or activity an entity had during a past period or in a historical context.
-
E.
historicalPass
Indicates that an entity has successfully completed or passed a historical event, period, or examination related to history.
- F. None of above. chosen
Provenance (4 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_69f349412c78819084459850e11d29f7 |
completed | April 30, 2026, 12:21 p.m. |
| NER | Named-entity recognition | batch_69ffb97b8ff8819088b105d99a0820c9 |
completed | May 9, 2026, 10:47 p.m. |
| PD | Predicate disambiguation | batch_69ffb88ef7388190a710120ed76edc0e |
completed | May 9, 2026, 10:43 p.m. |
| PDg | Predicate description generation | batch_69ffb97ae1508190bf3addd6e2aac281 |
completed | May 9, 2026, 10:47 p.m. |
Created at: May 1, 2026, 1:17 a.m.