Triple
T10122938
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | William Bligh |
E223342
|
entity |
| Predicate | familyName |
P18
|
FINISHED |
| Object | Bligh |
E223342
|
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: Bligh | Statement: [William Bligh, familyName, Bligh]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Bligh Context triple: [William Bligh, familyName, Bligh]
-
A.
Bligh
Bligh is the middle name of Malcolm Turnbull, the 29th Prime Minister of Australia.
-
B.
William Bligh
chosen
William Bligh was a British naval officer and navigator best known as the captain during the infamous mutiny on the HMS Bounty.
-
C.
Fletcher Christian
Fletcher Christian was a British naval officer best known for leading the mutiny on HMS Bounty against Captain William Bligh in 1789.
-
D.
Captain Nelson
Captain Nelson is the fictional U.S. Army paratroop officer who serves as the central protagonist in the World War II film "Objective, Burma!".
-
E.
Capt. Cook's
Capt. Cook's is a casual quick-service restaurant at Disney's Polynesian Village Resort known for serving Polynesian-inspired dishes and popular Disney park favorites.
- 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_69ca8422047c81909d66b717b8b18cf3 |
completed | March 30, 2026, 2:09 p.m. |
| NER | Named-entity recognition | batch_69cdd2ea7fe88190acb08d292a794638 |
completed | April 2, 2026, 2:22 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d2e5b6101081909c97956591b01af9 |
completed | April 5, 2026, 10:44 p.m. |
Created at: March 30, 2026, 9:05 p.m.