Triple
T17519388
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Encode OSS |
E426646
|
entity |
| Predicate | maintainer |
P2962
|
FINISHED |
| Object | Tom Christie |
—
|
NE NERFINISHED |
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: Tom Christie | Statement: [Encode OSS, maintainer, Tom Christie]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Tom Christie Context triple: [Encode OSS, maintainer, Tom Christie]
-
A.
Tom Christie
chosen
Tom Christie is a software developer best known for creating the Starlette ASGI framework and the Django REST framework in the Python ecosystem.
-
B.
Steve Christie
Steve Christie is a former NFL placekicker best known for his clutch performances with the Buffalo Bills in the early 1990s, including several game-winning playoff kicks.
-
C.
James Christie
James Christie was an 18th-century British auctioneer who founded the renowned auction house Christie's in London.
-
D.
Jonathan Chinn
Jonathan Chinn is a television and film producer known for his work in documentary and non-fiction programming.
-
E.
Jeremy Stevens
Jeremy Stevens is an American television and film writer best known for his work on comedy projects, including the screenplay for the 1985 film "Summer Rental."
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69d889de677081909b22d2657b1f0292 |
completed | April 10, 2026, 5:25 a.m. |
| NER | Named-entity recognition | batch_69e452d18c1c81908bb843bbddb44ca1 |
completed | April 19, 2026, 3:58 a.m. |
Created at: April 10, 2026, 5:49 a.m.