Triple
T7860107
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jemima Kirke |
E182472
|
entity |
| Predicate | workedOn |
P3
|
FINISHED |
| Object | Girls |
E246586
|
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: Girls | Statement: [Jemima Kirke, workedOn, Girls]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Girls Context triple: [Jemima Kirke, workedOn, Girls]
-
A.
Girls
"Girls" is a song by the Beastie Boys from their influential debut album "Licensed to Ill," known for its minimalist production and controversial, tongue-in-cheek lyrics about gender roles.
-
B.
Girls
chosen
Girls is an HBO comedy-drama television series created by and starring Lena Dunham that follows a group of young women navigating life and relationships in New York City.
-
C.
Girls
"Girls" is a hip-hop track by Kid Cudi from his album *Indicud*, known for its playful, upbeat production and focus on nightlife and relationships.
-
D.
Girl
"Girl" is Pharrell Williams' 2014 funk- and R&B-infused studio album known for its upbeat, soulful sound and the hit single "Happy."
-
E.
Girl
"Girl" is a 2005 pop-rock song by American musician Beck, known for its catchy melody and surreal, collage-style lyrics.
- 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_69ca82887fd48190975896bf38c4596b |
completed | March 30, 2026, 2:02 p.m. |
| NER | Named-entity recognition | batch_69cb36bb6ca4819098bc00739e07cfc8 |
completed | March 31, 2026, 2:51 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cbdf587efc819099e24ab2fad6d4be |
completed | March 31, 2026, 2:51 p.m. |
Created at: March 30, 2026, 4:53 p.m.