Triple
T10000002
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dr. Gillian Foster |
E197299
|
entity |
| Predicate | hasColleague |
P398
|
FINISHED |
| Object | Eli Loker |
E204344
|
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: Eli Loker | Statement: [Dr. Gillian Foster, hasColleague, Eli Loker]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Eli Loker Context triple: [Dr. Gillian Foster, hasColleague, Eli Loker]
-
A.
Eli Loker
chosen
Eli Loker is a character on the TV series "Lie to Me," known as a researcher and expert in detecting deception who works with the Lightman Group.
-
B.
John Loker
John Loker is a British abstract painter known for his large-scale, gestural works that explore space, movement, and perception.
-
C.
Eli Nunn
Eli Nunn is the child of English actress and writer Imogen Stubbs.
-
D.
Eli Meyer
Eli Meyer is one of the children of Stephenie Meyer, the bestselling author of the "Twilight" series.
-
E.
Spence Olchin
Spence Olchin is a socially awkward, nerdy friend character from the sitcom "The King of Queens," known for his quirky personality and close ties to the main couple.
- 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_69ca82f3b61c81908ecc2c1c96dbc2e4 |
completed | March 30, 2026, 2:04 p.m. |
| NER | Named-entity recognition | batch_69cdcc8dc9c081909b6d20909ada09cf |
completed | April 2, 2026, 1:55 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d26a36aadc81909978b71bdb3a6654 |
completed | April 5, 2026, 1:57 p.m. |
Created at: March 30, 2026, 8:51 p.m.