Triple
T6253803
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sacha Skarbek |
E140110
|
entity |
| Predicate | coWrote |
P7732
|
FINISHED |
| Object | Cold |
E448211
|
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: Cold | Statement: [Sacha Skarbek, coWrote, Cold]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Cold Context triple: [Sacha Skarbek, coWrote, Cold]
-
A.
Cold
"Cold" is an autobiographical book by British explorer Sir Ranulph Fiennes recounting his extreme polar expeditions and experiences in some of the harshest climates on Earth.
-
B.
Cold
"Cold" is a song by GOOD Music, best known for its collaboration between Kanye West and DJ Khaled that blends braggadocious lyrics with a hard-hitting, minimalist beat.
-
C.
Cold
chosen
"Cold" is a song by British singer-songwriter James Blunt, known for its emotive lyrics and melodic pop style.
-
D.
Ice Cold
Ice Cold is a suspenseful crime thriller novel by Tess Gerritsen featuring medical examiner Maura Isles stranded with a deadly secret in a remote, abandoned Wyoming community.
-
E.
Frías
Frías is a Spanish-language surname commonly found in Spain and Latin America.
- 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_69c008b4858c819095b0199114a9a87b |
completed | March 22, 2026, 3:20 p.m. |
| NER | Named-entity recognition | batch_69c063625608819081f5422112c80ce5 |
completed | March 22, 2026, 9:47 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c2442a556081908b91e7d999a82514 |
completed | March 24, 2026, 7:58 a.m. |
Created at: March 22, 2026, 4:24 p.m.