Triple
T18950080
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Susan Kelechi Watson |
E463622
|
entity |
| Predicate | heritageDetail |
P133915
|
FINISHED |
| Object | Nigerian Igbo |
—
|
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: Nigerian Igbo | Statement: [Susan Kelechi Watson, heritageDetail, Nigerian Igbo]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: heritageDetail Context triple: [Susan Kelechi Watson, heritageDetail, Nigerian Igbo]
-
A.
heritageType
Indicates the classification of an entity’s cultural or natural heritage category or type within a heritage framework.
-
B.
heritageReference
Indicates that one entity serves as a cultural, historical, or heritage-related reference or source for another entity.
-
C.
heritageService
Indicates that an entity provides, manages, or is associated with services related to the preservation, interpretation, or promotion of cultural or natural heritage.
-
D.
heritageLocation
Indicates that a location is recognized or designated as having cultural, historical, or natural heritage significance in relation to something.
-
E.
heritageRevealedBy
Indicates that an entity’s heritage or origin becomes known or is disclosed through a specified revealing event, source, or process.
- 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_69d8dcfec90481909e926be9767e5779 |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5d542b238819089ccd2df279a2f7f |
completed | April 20, 2026, 7:26 a.m. |
| PD | Predicate disambiguation | batch_69e4a2efec5c8190840704016bf547a1 |
completed | April 19, 2026, 9:40 a.m. |
| PDg | Predicate description generation | batch_69e4ad8e075c8190ad561edc5e520057 |
completed | April 19, 2026, 10:25 a.m. |
Created at: April 10, 2026, noon