Triple
T21629034
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | City of New Orleans |
E533778
|
entity |
| Predicate | recordedBy |
P1165
|
FINISHED |
| Object |
Mountain
Mountain is an American hard rock band, best known for their heavy blues-influenced sound and the classic rock hit "Mississippi Queen."
|
E1494154
|
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: Mountain | Statement: [City of New Orleans, recordedBy, Mountain]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mountain Context triple: [City of New Orleans, recordedBy, Mountain]
-
A.
Mountain
Mountain is the nickname of Harlan "Mountain" McClintock, a character from the television series The Twilight Zone.
-
B.
Mount
Mount is the surname of American actor Anson Mount, known for his roles in television series such as "Hell on Wheels" and "Star Trek: Discovery."
-
C.
Montagne
Montagne was a prominent French ship of the line that served as the flagship of the French fleet during the late 18th century.
-
D.
Mount Scenery
Mount Scenery is a dormant volcano and the highest peak in the Kingdom of the Netherlands, located on the Caribbean island of Saba.
-
E.
Mountains
Mountains is an episode of the BBC nature documentary series Planet Earth II that explores wildlife and ecosystems in some of the world’s highest and most remote mountain ranges.
- 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: Mountain Triple: [City of New Orleans, recordedBy, Mountain]
Generated description
Mountain is an American hard rock band, best known for their heavy blues-influenced sound and the classic rock hit "Mississippi Queen."
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Mountain Target entity description: Mountain is an American hard rock band, best known for their heavy blues-influenced sound and the classic rock hit "Mississippi Queen."
-
A.
Mountain
Mountain is the nickname of Harlan "Mountain" McClintock, a character from the television series The Twilight Zone.
-
B.
Mount
Mount is the surname of American actor Anson Mount, known for his roles in television series such as "Hell on Wheels" and "Star Trek: Discovery."
-
C.
Montagne
Montagne was a prominent French ship of the line that served as the flagship of the French fleet during the late 18th century.
-
D.
Mount Scenery
Mount Scenery is a dormant volcano and the highest peak in the Kingdom of the Netherlands, located on the Caribbean island of Saba.
-
E.
Mountains
Mountains is an episode of the BBC nature documentary series Planet Earth II that explores wildlife and ecosystems in some of the world’s highest and most remote mountain ranges.
- 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_69e0c464fba881908d0ff2ac80511ce1 |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69ef5215ae3c81909e6dedba23822970 |
completed | April 27, 2026, 12:09 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0a0f9531b08190bbddca01060f20ae |
completed | May 17, 2026, 6:57 p.m. |
| NEDg | Description generation | batch_6a0a108bf4608190af587dd34077f2ad |
completed | May 17, 2026, 7:01 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a0a110507d48190ad75223311ce159e |
completed | May 17, 2026, 7:03 p.m. |
Created at: April 16, 2026, 6:34 p.m.