Triple
T2569102
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Thoby Stephen |
E57621
|
entity |
| Predicate | givenName |
P17
|
FINISHED |
| Object | Adrian |
E137635
|
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: Adrian | Statement: [Thoby Stephen, givenName, Adrian]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Adrian Context triple: [Thoby Stephen, givenName, Adrian]
-
A.
Adrian
chosen
Adrian was a renowned Hollywood costume designer best known for creating glamorous and influential fashions for classic MGM films of the 1930s and 1940s.
-
B.
Andreas
Andreas is a masculine given name of Greek origin, commonly used in various European and international cultures.
-
C.
Alec
Alec is the familiar nickname of Alec Douglas-Home, a British Conservative politician who served as Prime Minister of the United Kingdom from 1963 to 1964.
-
D.
Julian Dennison
Julian Dennison is a New Zealand actor best known for his breakout role in "Hunt for the Wilderpeople" and his performance in "Deadpool 2."
-
E.
Tobias
Tobias was a Native American man from the 17th-century Wampanoag community, known primarily through his familial connection to the Sakonnet leader Awashonks.
- 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_69ab4a51410081908501dcf8bad9adc4 |
completed | March 6, 2026, 9:42 p.m. |
| NER | Named-entity recognition | batch_69abd380d6e081909c124e8a0b7feef3 |
completed | March 7, 2026, 7:28 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69af6569e38881908d1492277fe0c60c |
completed | March 10, 2026, 12:27 a.m. |
Created at: March 6, 2026, 9:48 p.m.