Triple
T6349407
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sofia |
E142830
|
entity |
| Predicate | forcedLabor |
P27275
|
FINISHED |
| Object | domestic servitude |
—
|
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: domestic servitude | Statement: [Sofia, forcedLabor, domestic servitude]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: forcedLabor Context triple: [Sofia, forcedLabor, domestic servitude]
-
A.
usedForcedLabor
chosen
Indicates that an entity compelled people to work against their will, typically under coercion, threat, or without fair compensation.
-
B.
labourOf
Indicates that one entity is the work, effort, or labor performed or contributed by another entity.
-
C.
hasInmateLabor
Indicates that an entity utilizes or is associated with labor performed by incarcerated individuals.
-
D.
laborProvision
Indicates the provision or supply of labor or workforce from one party to another for work or services.
-
E.
laborSystem
Indicates the type or structure of work organization, employment arrangements, and labor relations that govern how work is performed and managed.
- 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_69c008d6dcbc8190aa1c2f1fd8916b42 |
completed | March 22, 2026, 3:20 p.m. |
| NER | Named-entity recognition | batch_69c067bcec2c8190bb383605847b0f0b |
completed | March 22, 2026, 10:05 p.m. |
| PD | Predicate disambiguation | batch_69c060ea1a988190889e47b7e0c819b8 |
completed | March 22, 2026, 9:36 p.m. |
Created at: March 22, 2026, 4:31 p.m.