Triple
T14670727
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Celine Rattray |
E344503
|
entity |
| Predicate | notableWork |
P4
|
FINISHED |
| Object | Ten Thousand Saints |
E1044855
|
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: Ten Thousand Saints | Statement: [Celine Rattray, notableWork, Ten Thousand Saints]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Ten Thousand Saints Context triple: [Celine Rattray, notableWork, Ten Thousand Saints]
-
A.
Ten Thousand Saints
chosen
Ten Thousand Saints is a coming-of-age drama film set in 1980s New York City that explores youth, punk culture, and family dysfunction.
-
B.
Tears of God
"Tears of God" is a song featured on the album *By the Light of the Moon* by the American rock band Los Lobos.
-
C.
Saviors
Saviors is an album titled "Goodnight Adeline."
-
D.
Saviors
Saviors is a musical group or act best known for creating and performing the song "Father to a Son."
-
E.
Saviors
Saviors is a studio album by Green Day frontman Billie Joe Armstrong’s band, known for its politically charged punk rock sound and socially conscious themes.
- 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_69d822e283fc8190a0e4c235cf880052 |
completed | April 9, 2026, 10:06 p.m. |
| NER | Named-entity recognition | batch_69deb54ef2908190b189ced65eec434a |
completed | April 14, 2026, 9:44 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fde17a39b88190b144b6cfcc61a4b8 |
completed | May 8, 2026, 1:13 p.m. |
Created at: April 10, 2026, 1:27 a.m.