Triple
T6994049
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Roy Innis |
E162157
|
entity |
| Predicate | placeOfBirth |
P1
|
FINISHED |
| Object | St. Croix |
E27010
|
NE 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: St. Croix | Statement: [Roy Innis, placeOfBirth, St. Croix]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: St. Croix Context triple: [Roy Innis, placeOfBirth, St. Croix]
-
A.
Saint Croix
chosen
Saint Croix is the largest of the U.S. Virgin Islands, known for its historic towns, Caribbean beaches, and blend of Danish colonial and Afro-Caribbean culture.
-
B.
Lucea
Lucea is a coastal town in western Jamaica that serves as the capital of Hanover Parish and is known for its historic harbor and Georgian architecture.
-
C.
Roatán
Roatán is a popular Honduran island in the Caribbean Sea known for its coral reefs, beaches, and scuba diving tourism.
-
D.
Water Island
Water Island is a small, largely residential and tranquil island in the Caribbean that forms part of the U.S. Virgin Islands.
-
E.
Virgin Island
Virgin Island is a small, scenic islet off Bantayan Island in the Philippines, known for its white-sand beaches and clear turquoise waters.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69c68856d7808190ab33ee914640281b |
completed | March 27, 2026, 1:38 p.m. |
| NER | Named-entity recognition | batch_69c6dbeaa88c8190a49f8504c1793e1f |
completed | March 27, 2026, 7:35 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c76a1adec88190a769ec7af0fa7b51 |
completed | March 28, 2026, 5:41 a.m. |
Created at: March 27, 2026, 2:32 p.m.