Triple
T14942491
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Safe Haven |
E372564
|
entity |
| Predicate | musicBy |
P1952
|
FINISHED |
| Object | Deborah Lurie |
E807890
|
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: Deborah Lurie | Statement: [Safe Haven, musicBy, Deborah Lurie]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Deborah Lurie Context triple: [Safe Haven, musicBy, Deborah Lurie]
-
A.
Deborah Lurie
chosen
Deborah Lurie is an American composer and arranger known for her work on numerous film scores and soundtracks.
-
B.
Tovah Feldshuh
Tovah Feldshuh is an American actress and singer known for her work on stage, film, and television, including acclaimed performances on Broadway and in series like "The Walking Dead."
-
C.
Deborah S. Craig
Deborah S. Craig is an American actress, writer, and producer known for her work in television and theater, including creative roles on genre series like Tales of the Walking Dead.
-
D.
Gail Berke
Gail Berke is a central protagonist in the adventure film "The Deep," known for becoming entangled in a dangerous underwater treasure hunt.
-
E.
Ruth Pomerance
Ruth Pomerance is a film and theater producer known for her work on the production of "A Master Builder."
- 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_69d85cc9da0c81908d583ca3f63a3908 |
completed | April 10, 2026, 2:13 a.m. |
| NER | Named-entity recognition | batch_69ded68c1df0819084c0cd61b207d398 |
completed | April 15, 2026, 12:06 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fe7e929f3881908560b8428e72327d |
completed | May 9, 2026, 12:23 a.m. |
Created at: April 10, 2026, 2:38 a.m.