Triple
T13027547
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Share My World |
E326346
|
entity |
| Predicate | producer |
P490
|
FINISHED |
| Object | Malcolm Jamal-Warner |
E340987
|
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: Malcolm Jamal-Warner | Statement: [Share My World, producer, Malcolm Jamal-Warner]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Malcolm Jamal-Warner Context triple: [Share My World, producer, Malcolm Jamal-Warner]
-
A.
Malcolm-Jamal Warner
chosen
Malcolm-Jamal Warner is an American actor and director best known for his role as Theo Huxtable on the groundbreaking sitcom "The Cosby Show."
-
B.
Malcolm Johnson
Malcolm Johnson is the protagonist of the horror story "A Haunted House," around whom the eerie and supernatural events of the narrative revolve.
-
C.
Malcolm Smith
Malcolm Smith is an American former NFL linebacker best known for his standout performance with the Seattle Seahawks, including earning Super Bowl XLVIII Most Valuable Player honors.
-
D.
Malcolm Wilson
Malcolm Wilson was an American Republican politician who served as governor of New York in the early 1970s.
-
E.
Malcolm Byrne
Malcolm Byrne is a historian and analyst known for his work on U.S. foreign policy and declassified government documents, often in collaboration with fellow researcher Peter Kornbluh.
- 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_69d8076cc45c81908123123f43e69266 |
completed | April 9, 2026, 8:09 p.m. |
| NER | Named-entity recognition | batch_69d97efc07488190a15f3e41ea2db45c |
completed | April 10, 2026, 10:51 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f6c11f83d88190bc153dba75db0995 |
completed | May 3, 2026, 3:29 a.m. |
Created at: April 9, 2026, 8:53 p.m.