Triple
T1648837
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kelis |
E35644
|
entity |
| Predicate | single |
P3283
|
FINISHED |
| Object | Milkshake |
E186269
|
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: Milkshake | Statement: [Kelis, single, Milkshake]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Milkshake Context triple: [Kelis, single, Milkshake]
-
A.
Milkshake
chosen
"Milkshake" is a 2003 R&B song by American singer Kelis, best known for its catchy hook and enduring pop-culture presence.
-
B.
Blue Milk
Blue Milk is a famous Star Wars-themed, plant-based frozen drink served at Disney’s Galaxy’s Edge that recreates the iconic blue bantha milk seen in the films.
-
C.
Lollipop
"Lollipop" is a 2008 hit hip-hop single by Lil Wayne that became one of his most commercially successful and culturally influential songs.
-
D.
Juice
"Juice" is a 1992 crime drama film starring Tupac Shakur as a troubled Harlem teenager caught up in escalating violence and the pursuit of power.
-
E.
Peaches & Cream
"Peaches & Cream" is a popular R&B single by the group 112, known for its smooth, sensual sound and early-2000s chart success.
- 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_69a8860568888190a32cd9f70acbba42 |
completed | March 4, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69a90a6537e0819082b966023e0c0583 |
completed | March 5, 2026, 4:45 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ad681db3408190a3b469e319486419 |
completed | March 8, 2026, 12:14 p.m. |
Created at: March 4, 2026, 7:29 p.m.