Triple
T9015689
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tuck Everlasting |
E215587
|
entity |
| Predicate | screenwriter |
P2831
|
FINISHED |
| Object | Jeffrey Lieber |
E388250
|
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: Jeffrey Lieber | Statement: [Tuck Everlasting, screenwriter, Jeffrey Lieber]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Jeffrey Lieber Context triple: [Tuck Everlasting, screenwriter, Jeffrey Lieber]
-
A.
Jeffrey Lieber
chosen
Jeffrey Lieber is an American screenwriter and producer best known for his early role in developing the hit television series "Lost."
-
B.
Michael Glouberman
Michael Glouberman is a television writer and producer best known for his work on the acclaimed sitcom "Malcolm in the Middle."
-
C.
Kenneth Roth
Kenneth Roth is an American lawyer and human rights advocate best known for serving as the longtime executive director of Human Rights Watch.
-
D.
Paul Geleff
Paul Geleff was a Danish socialist politician and activist known as one of the pioneering figures in the early Danish labor and social democratic movement.
-
E.
Andrew Weisblum
Andrew Weisblum is an American film editor known for his work on major feature films, including collaborations with directors like Darren Aronofsky and Wes Anderson.
- 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_69ca83a38aa88190bf1bb80c4548b5e2 |
completed | March 30, 2026, 2:07 p.m. |
| NER | Named-entity recognition | batch_69cc69fc0e4c819080b60456375f94cd |
completed | April 1, 2026, 12:42 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cfdba8bd8c81909860d561d9d16611 |
completed | April 3, 2026, 3:24 p.m. |
Created at: March 30, 2026, 7:06 p.m.