Triple
T3736870
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Rohingya |
E79605
|
entity |
| Predicate | majorExodus |
P43380
|
FINISHED |
| Object | 2017 |
—
|
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: 2017 | Statement: [Rohingya, majorExodus, 2017]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: majorExodus Context triple: [Rohingya, majorExodus, 2017]
-
A.
majorDeportation
Indicates that an entity was subjected to a large-scale, often forced, removal or expulsion from a country or region.
-
B.
hasSignificantEmigrationTo
chosen
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.
majorExport
Indicates that something is a primary or significant export product or resource of a given entity (such as a country or region).
-
D.
majorExpansionUnder
Indicates that one entity is undergoing or has undergone a significant enlargement, growth, or extension while being under the authority, control, or scope of another entity.
-
E.
majorMassacre
Indicates a relationship where an event involves the large-scale, deliberate killing of many individuals, typically characterized by extreme violence and high casualty numbers.
- 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_69ad8b115610819095b02007da5ca3cb |
completed | March 8, 2026, 2:43 p.m. |
| NER | Named-entity recognition | batch_69adcb3d32b081909a993a78b0869db8 |
completed | March 8, 2026, 7:17 p.m. |
| PD | Predicate disambiguation | batch_69adc04746588190b0dc535638f23546 |
completed | March 8, 2026, 6:30 p.m. |
Created at: March 8, 2026, 3:34 p.m.