Triple
T36393450
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Banlam people |
E896394
|
entity |
| Predicate | historicalMigrationDestination |
P174496
|
FINISHED |
| Object | Taiwan |
—
|
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: Taiwan | Statement: [Banlam people, historicalMigrationDestination, Taiwan]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: historicalMigrationDestination Context triple: [Banlam people, historicalMigrationDestination, Taiwan]
-
A.
immigrationDestinationFor
chosen
Indicates that a location serves as the destination to which an entity immigrates.
-
B.
hasSignificantEmigrationTo
Indicates that a substantial number of people leave one place, group, or entity to move and settle in another specific place, group, or entity.
-
C.
immigratedTo
Indicates that an entity moved from its country of origin to live permanently in another specified country or region.
-
D.
mainDeportationDestination
Indicates the primary location to which individuals are deported in a given deportation event or process.
-
E.
historicalMigrationType
Indicates the type or category of migration that occurred in a historical context between entities.
- 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_69f76e52e3108190becf70b090ae7bd6 |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_6a012594c27081908c80f0e0e6010290 |
completed | May 11, 2026, 12:40 a.m. |
| PD | Predicate disambiguation | batch_6a01252350548190b1df9edc9e581e91 |
completed | May 11, 2026, 12:38 a.m. |
Created at: May 3, 2026, 4:10 p.m.