Triple
T10806168
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ellis Library |
E254971
|
entity |
| Predicate | city |
P40
|
FINISHED |
| Object |
Columbia
Columbia is a mid-sized Missouri city best known as the home of the University of Missouri and a regional center for education, healthcare, and culture.
|
E258546
|
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: Columbia | Statement: [Ellis Library, city, Columbia]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Columbia Context triple: [Ellis Library, city, Columbia]
-
A.
Columbia
Columbia is a major American record label known for signing and releasing music by many influential artists across genres.
-
B.
Columbia
Columbia was the command module spacecraft of NASA's historic Apollo 11 mission, which carried astronauts to the Moon and safely returned them to Earth in 1969.
-
C.
Columbia
Columbia is a small unincorporated community located in the state of Iowa in the United States.
-
D.
Columbia
Columbia was the former name of the John F. Kennedy/University of Massachusetts Boston subway station on Boston’s MBTA Red Line.
-
E.
Columbia
Columbia is an outdoor apparel and footwear brand known for its durable, weather-resistant gear for activities like hiking, skiing, and camping.
- 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: Columbia Triple: [Ellis Library, city, Columbia]
Generated description
Columbia is a mid-sized Missouri city best known as the home of the University of Missouri and a regional center for education, healthcare, and culture.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Columbia Target entity description: Columbia is a mid-sized Missouri city best known as the home of the University of Missouri and a regional center for education, healthcare, and culture.
-
A.
Columbia
chosen
Columbia is a mid-sized city in central Missouri known as a major college town and cultural hub, home to the University of Missouri and several other educational institutions.
-
B.
Columbia
Columbia is the capital city of South Carolina, known for hosting the University of South Carolina and its prominent Gamecocks athletic programs.
-
C.
Columbia
Columbia is a large planned community in central Maryland known for its suburban neighborhoods, extensive green spaces, and mixed-use town centers.
-
D.
Columbia
Columbia is a small unincorporated community located in the state of Iowa in the United States.
-
E.
Columbia
Columbia is a historical and poetic personification of the United States, often used as a national symbol in literature, art, and place names.
- F. None of above.
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_69d6aa61c15c8190a1839550c56e75e1 |
completed | April 8, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69d733b3f92c8190bcc85db22d77bb7d |
completed | April 9, 2026, 5:05 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69de554ed3848190bba56ab52c05902c |
completed | April 14, 2026, 2:55 p.m. |
| NEDg | Description generation | batch_69de5952f6c48190abd3b87372d54f58 |
completed | April 14, 2026, 3:12 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69de5ed49c9c8190a4085407f88d7a05 |
completed | April 14, 2026, 3:35 p.m. |
Created at: April 8, 2026, 9:18 p.m.