Triple
T14727948
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Love Letter |
E345991
|
entity |
| Predicate | hasTrack |
P3284
|
FINISHED |
| Object |
Taxi Cab
"Taxi Cab" is a song by the American rock band The Killers, featured as a track on their 2004 compilation album "Sawdust."
|
E1115307
|
NE FINISHED |
How this triple was built (4 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: Taxi Cab | Statement: [Love Letter, hasTrack, Taxi Cab]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Taxi Cab Context triple: [Love Letter, hasTrack, Taxi Cab]
-
A.
Taxi
Taxi is a 2015 Iranian docu-fiction film directed by Jafar Panahi, set almost entirely inside a Tehran taxi as it explores everyday life and social issues in contemporary Iran.
-
B.
Taxi
Taxi is a critically acclaimed American sitcom that aired from 1978 to 1983, following the lives of New York City cab drivers and their dispatcher, and is celebrated for its ensemble cast and blend of comedy and pathos.
-
C.
Taxi for Two
Taxi for Two is a song by the pop group The Taxi Boys.
-
D.
Taksi
Taksi was a Jurchen chieftain of the late Ming period and the father of Nurhaci, whose lineage helped lay the foundations for the later Qing dynasty.
-
E.
The Cab Driver
The Cab Driver is the alias of Darryl Hill, a figure known primarily in connection with his activities under this moniker.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Taxi Cab Triple: [Love Letter, hasTrack, Taxi Cab]
Generated description
"Taxi Cab" is a song by the American rock band The Killers, featured as a track on their 2004 compilation album "Sawdust."
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Taxi Cab Target entity description: "Taxi Cab" is a song by the American rock band The Killers, featured as a track on their 2004 compilation album "Sawdust."
-
A.
Taxi
Taxi is a 2015 Iranian docu-fiction film directed by Jafar Panahi, set almost entirely inside a Tehran taxi as it explores everyday life and social issues in contemporary Iran.
-
B.
Taxi
Taxi is a critically acclaimed American sitcom that aired from 1978 to 1983, following the lives of New York City cab drivers and their dispatcher, and is celebrated for its ensemble cast and blend of comedy and pathos.
-
C.
Taxi for Two
Taxi for Two is a song by the pop group The Taxi Boys.
-
D.
Taksi
Taksi was a Jurchen chieftain of the late Ming period and the father of Nurhaci, whose lineage helped lay the foundations for the later Qing dynasty.
-
E.
The Cab Driver
The Cab Driver is the alias of Darryl Hill, a figure known primarily in connection with his activities under this moniker.
- F. None of above. chosen
Provenance (5 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_69d822e5911c8190ba589f957dbd9ba7 |
completed | April 9, 2026, 10:06 p.m. |
| NER | Named-entity recognition | batch_69dec26179688190ba9f3cd045da0e2a |
completed | April 14, 2026, 10:40 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fdf099eaf48190b89032b6ac769e67 |
completed | May 8, 2026, 2:18 p.m. |
| NEDg | Description generation | batch_69fdf20f3f0c81909052226a1fb8f165 |
completed | May 8, 2026, 2:24 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69fdf30dab20819085589da4e869fb7e |
completed | May 8, 2026, 2:28 p.m. |
Created at: April 10, 2026, 1:29 a.m.