Triple
T4168589
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ms. Jackson |
E84503
|
entity |
| Predicate | writer |
P1360
|
FINISHED |
| Object | David Sheats |
E332377
|
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: David Sheats | Statement: [Ms. Jackson, writer, David Sheats]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: David Sheats Context triple: [Ms. Jackson, writer, David Sheats]
-
A.
David Sheats
chosen
David Sheats, better known as Mr. DJ, is an American hip hop producer and DJ best known for his work with the Atlanta rap duo Outkast.
-
B.
Peter Scolari
Peter Scolari was an American actor best known for his comedic and character roles on television series such as "Bosom Buddies" and "Newhart."
-
C.
Sergio Costa
Sergio Costa is a businessman best known as the co-founder of Costa Coffee, one of the largest coffeehouse chains in the world.
-
D.
Óscar Pareja
Óscar Pareja is a Colombian soccer manager and former midfielder known for his successful coaching stints in Major League Soccer, including with FC Dallas and Orlando City SC.
-
E.
Alejandro Gillick
Alejandro Gillick is a mysterious and ruthless former prosecutor turned covert operative who serves as a key enforcer in the Sicario film series.
- 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_69aed932cab48190b80ffe35f7029ae1 |
completed | March 9, 2026, 2:29 p.m. |
| NER | Named-entity recognition | batch_69af02c573788190a60ab3f83b07a6f6 |
completed | March 9, 2026, 5:26 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b57f4c2c988190959496cc0cc31cac |
completed | March 14, 2026, 3:31 p.m. |
Created at: March 9, 2026, 3:44 p.m.