Triple
T10016103
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Travis Gibb |
E199498
|
entity |
| Predicate | sibling |
P363
|
FINISHED |
| Object | Alexandra Gibb |
E213492
|
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: Alexandra Gibb | Statement: [Travis Gibb, sibling, Alexandra Gibb]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Alexandra Gibb Context triple: [Travis Gibb, sibling, Alexandra Gibb]
-
A.
Alexandra Gibb
chosen
Alexandra Gibb is a television and film producer best known as the daughter of Bee Gees singer-songwriter Barry Gibb.
-
B.
Alexandra Byrne
Alexandra Byrne is an acclaimed British costume designer known for her intricate period costumes and award-winning work in both film and theatre.
-
C.
Gabrielle Allan
Gabrielle Allan is a television writer and producer known for her work on comedy series, including co-creating the animated show "HouseBroken."
-
D.
Heather Gibson
Heather Gibson is known as the wife of the late British actor Richard Griffiths, acclaimed for his roles in film, television, and theatre.
-
E.
Sarah Gurling
Sarah Gurling is best known as the wife of the late British Liberal Democrat leader Charles Kennedy.
- 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_69ca8315a1a08190ab310f25620f362b |
completed | March 30, 2026, 2:05 p.m. |
| NER | Named-entity recognition | batch_69cdcd4ad3348190bae03cd37c787674 |
completed | April 2, 2026, 1:58 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d354d7202c81908d42107c346900dc |
completed | April 6, 2026, 6:38 a.m. |
Created at: March 30, 2026, 8:52 p.m.