Triple
T11421840
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mark Sanger |
E270641
|
entity |
| Predicate | notableWork |
P4
|
FINISHED |
| Object | Gravity |
E38378
|
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: Gravity | Statement: [Mark Sanger, notableWork, Gravity]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Gravity Context triple: [Mark Sanger, notableWork, Gravity]
-
A.
Gravity
"Gravity" is a poignant piano-driven ballad by Sara Bareilles that explores the emotional pull of a difficult, lingering relationship.
-
B.
Gravity
"Gravity" is a song by the American rock band Our Lady Peace from their 2002 album of the same name.
-
C.
Gravity
chosen
Gravity is a 2013 science fiction thriller film directed by Alfonso Cuarón that follows astronauts stranded in space after their shuttle is destroyed.
-
D.
Gravity
"Gravity" is a soulful blues-rock ballad by John Mayer, celebrated for its expressive guitar work and introspective lyrics.
-
E.
Gravity
"Gravity" is a medical thriller novel by Tess Gerritsen that combines space-station suspense with biomedical disaster.
- 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_69d6aaddeaa8819088b30ef7b50598c9 |
completed | April 8, 2026, 7:22 p.m. |
| NER | Named-entity recognition | batch_69d801b357e88190ace56d36a945688f |
completed | April 9, 2026, 7:44 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69e5b8a1e88c8190994bea88a0490e60 |
completed | April 20, 2026, 5:24 a.m. |
Created at: April 8, 2026, 9:34 p.m.