Triple
T1617021
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Gillian |
E34741
|
entity |
| Predicate | isCognateOf |
P2527
|
FINISHED |
| Object | Jillian |
E190234
|
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: Jillian | Statement: [Gillian, isCognateOf, Jillian]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Jillian Context triple: [Gillian, isCognateOf, Jillian]
-
A.
Jillian
chosen
Jillian is a feminine given name, commonly considered a variant of Gillian and used in English-speaking countries.
-
B.
Jillian Russell
Jillian Russell is a recurring character on the animated TV show "Family Guy," known as Brian Griffin’s attractive but somewhat dim-witted human girlfriend.
-
C.
Gianna
Gianna is a feminine given name of Italian origin, often associated with the late Gianna Bryant, daughter of basketball legend Kobe Bryant.
-
D.
Jill Sinclair
Jill Sinclair was a British businesswoman and influential music industry executive who co-founded the ZTT record label and the Sarm Studios complex.
-
E.
Hayley
Hayley is a Canadian former ice hockey player widely regarded as one of the greatest female hockey players of all time.
- 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_69a885ffc5ec819091afa325d5f9611c |
completed | March 4, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69a909abbec081908f95547471530ad5 |
completed | March 5, 2026, 4:42 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ad8ab5e8b88190b95af87391e5bb16 |
completed | March 8, 2026, 2:41 p.m. |
Created at: March 4, 2026, 7:28 p.m.