Triple
T704217
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Southern Company |
E14064
|
entity |
| Predicate | tickerSymbol |
P1447
|
FINISHED |
| Object |
SO
SO is the New York Stock Exchange ticker symbol for Southern Company, a major U.S. electric and gas utility holding company based in the Southeast.
|
E86592
|
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: SO | Statement: [Southern Company, tickerSymbol, SO]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: SO Context triple: [Southern Company, tickerSymbol, SO]
-
A.
SO
SO is the two-letter ISO 3166-1 alpha-2 country code assigned to Somalia for international identification and data standards.
-
B.
S
S is the New York City Subway service designation used for the 42nd Street Shuttle, a short line connecting Times Square and Grand Central in Manhattan.
-
C.
S
S is the distinctive middle initial of U.S. President Harry S. Truman, famously not standing for any specific name but honoring both of his grandfathers.
-
D.
SE
SE is the two-letter ISO 3166-1 alpha-2 country code that uniquely identifies Sweden in international standards and systems.
-
E.
Sol
Sol is the Sun, the G-type main-sequence star at the center of our solar system that provides Earth with light and heat.
- 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: SO Triple: [Southern Company, tickerSymbol, SO]
Generated description
SO is the New York Stock Exchange ticker symbol for Southern Company, a major U.S. electric and gas utility holding company based in the Southeast.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: SO Target entity description: SO is the New York Stock Exchange ticker symbol for Southern Company, a major U.S. electric and gas utility holding company based in the Southeast.
-
A.
SO
SO is the two-letter ISO 3166-1 alpha-2 country code assigned to Somalia for international identification and data standards.
-
B.
S
S is the New York City Subway service designation used for the 42nd Street Shuttle, a short line connecting Times Square and Grand Central in Manhattan.
-
C.
S
S is the distinctive middle initial of U.S. President Harry S. Truman, famously not standing for any specific name but honoring both of his grandfathers.
-
D.
SE
SE is the two-letter ISO 3166-1 alpha-2 country code that uniquely identifies Sweden in international standards and systems.
-
E.
Sol
Sol is the Sun, the G-type main-sequence star at the center of our solar system that provides Earth with light and heat.
- 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_69a493494ec48190ae6751683625a9ba |
completed | March 1, 2026, 7:28 p.m. |
| NER | Named-entity recognition | batch_69a4a533fa788190bba0f55655469c46 |
completed | March 1, 2026, 8:44 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69a63755d1f081909f214ab8d497f096 |
completed | March 3, 2026, 1:20 a.m. |
| NEDg | Description generation | batch_69a63af75b1881908fa959febc48775e |
completed | March 3, 2026, 1:35 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69a63b60e96c8190b4f13bd7076af38a |
completed | March 3, 2026, 1:37 a.m. |
Created at: March 1, 2026, 7:36 p.m.