Triple
T8074839
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Paul Morrissey |
E188464
|
entity |
| Predicate | directed |
P7373
|
FINISHED |
| Object | Mixed Blood |
E710232
|
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: Mixed Blood | Statement: [Paul Morrissey, directed, Mixed Blood]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mixed Blood Context triple: [Paul Morrissey, directed, Mixed Blood]
-
A.
Mixed Blood
chosen
Mixed Blood is a 1985 crime drama film directed by Paul Morrissey that portrays gang conflicts and survival in New York City's Lower East Side.
-
B.
Half-Breed
"Half-Breed" is a 1973 pop song by Cher that became one of her signature hits, noted for its storytelling about a mixed-race Native American woman's struggles.
-
C.
In My Blood
"In My Blood" is a 2016 electropop single by Australian pop duo The Veronicas, known for its pulsating synth-driven production and emotionally charged lyrics about obsessive love.
-
D.
Mulatto
"Mulatto" is a 1935 play by Langston Hughes that explores race, identity, and family conflict in the Jim Crow American South.
-
E.
Bloods
Bloods is a predominantly African-American street gang that originated in Los Angeles and is known for its rivalry with the Crips and its nationwide network of affiliated sets.
- 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_69ca82b50c708190863f661d438e68df |
completed | March 30, 2026, 2:03 p.m. |
| NER | Named-entity recognition | batch_69cb404c513c8190af54d6d6b6d1a81d |
completed | March 31, 2026, 3:32 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cc93e568388190a518baa0badefea4 |
completed | April 1, 2026, 3:41 a.m. |
Created at: March 30, 2026, 5:27 p.m.