Triple
T676798
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Baltimore |
E13094
|
entity |
| Predicate | hasMayor |
P185
|
FINISHED |
| Object |
Brandon Scott
Brandon Scott is an American politician serving as the mayor of Baltimore, Maryland.
|
E162193
|
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: Brandon Scott | Statement: [Baltimore, hasMayor, Brandon Scott]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Brandon Scott Context triple: [Baltimore, hasMayor, Brandon Scott]
-
A.
Darnell Scott
Darnell Scott is a music producer best known for his work on The Notorious B.I.G.’s landmark debut album "Ready to Die."
-
B.
Isaiah Rogers
Isaiah Rogers was a prominent 19th-century American architect known for pioneering hotel design and contributing major public buildings in the United States.
-
C.
T. J. Holmes
T. J. Holmes is an American journalist and television personality best known as a former CNN anchor and co-host of ABC’s “GMA3: What You Need to Know.”
-
D.
Matthew Kirk
Matthew Kirk is a notable individual who shares the surname Kirk, recognized for achievements significant enough to be distinguished among others with the same name.
-
E.
Nick Hendricks
Nick Hendricks is a frustrated office worker from the dark comedy film "Horrible Bosses," who conspires with his friends to murder their abusive employers.
- 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: Brandon Scott Triple: [Baltimore, hasMayor, Brandon Scott]
Generated description
Brandon Scott is an American politician serving as the mayor of Baltimore, Maryland.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Brandon Scott Target entity description: Brandon Scott is an American politician serving as the mayor of Baltimore, Maryland.
-
A.
Darnell Scott
Darnell Scott is a music producer best known for his work on The Notorious B.I.G.’s landmark debut album "Ready to Die."
-
B.
Isaiah Rogers
Isaiah Rogers was a prominent 19th-century American architect known for pioneering hotel design and contributing major public buildings in the United States.
-
C.
T. J. Holmes
T. J. Holmes is an American journalist and television personality best known as a former CNN anchor and co-host of ABC’s “GMA3: What You Need to Know.”
-
D.
Matthew Kirk
Matthew Kirk is a notable individual who shares the surname Kirk, recognized for achievements significant enough to be distinguished among others with the same name.
-
E.
Nick Hendricks
Nick Hendricks is a frustrated office worker from the dark comedy film "Horrible Bosses," who conspires with his friends to murder their abusive employers.
- 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_69a4933d3bf88190972041cd8cf143b9 |
completed | March 1, 2026, 7:27 p.m. |
| NER | Named-entity recognition | batch_69a4a04b2ae881908a5c23453bef8572 |
completed | March 1, 2026, 8:23 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ace52cf51881909ab5dc361d342ce7 |
completed | March 8, 2026, 2:55 a.m. |
| NEDg | Description generation | batch_69ace5bb634c8190889206182da1d2ed |
completed | March 8, 2026, 2:58 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69ace63be9508190b5b0e7c9d7af57f0 |
completed | March 8, 2026, 3 a.m. |
Created at: March 1, 2026, 7:36 p.m.