Triple
T857852
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Addie Mae Collins |
E18532
|
entity |
| Predicate | familyName |
P18
|
FINISHED |
| Object |
Collins
Collins is a common English-language surname borne by numerous notable individuals across fields such as politics, sports, literature, and entertainment.
|
E101754
|
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: Collins | Statement: [Addie Mae Collins, familyName, Collins]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Collins Context triple: [Addie Mae Collins, familyName, Collins]
-
A.
Cassell
Cassell is a British publishing company known for producing a wide range of books, including notable historical works and reference titles.
-
B.
Langway
Langway is the surname of Rod Langway, a Hall of Fame National Hockey League defenseman known for his defensive prowess with the Washington Capitals.
-
C.
COLL
COLL is the standard abbreviation for the Division of Colloid and Surface Chemistry, a professional body focused on research and advancement in colloid and surface science.
-
D.
Aldous
Aldous is a masculine given name most famously borne by the English writer and philosopher Aldous Huxley.
-
E.
HOLLIS
HOLLIS is Harvard University's integrated online library catalog and discovery system for accessing its vast collections of books, media, and digital resources.
- 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: Collins Triple: [Addie Mae Collins, familyName, Collins]
Generated description
Collins is a common English-language surname borne by numerous notable individuals across fields such as politics, sports, literature, and entertainment.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Collins Target entity description: Collins is a common English-language surname borne by numerous notable individuals across fields such as politics, sports, literature, and entertainment.
-
A.
Cassell
Cassell is a British publishing company known for producing a wide range of books, including notable historical works and reference titles.
-
B.
Langway
Langway is the surname of Rod Langway, a Hall of Fame National Hockey League defenseman known for his defensive prowess with the Washington Capitals.
-
C.
COLL
COLL is the standard abbreviation for the Division of Colloid and Surface Chemistry, a professional body focused on research and advancement in colloid and surface science.
-
D.
Aldous
Aldous is a masculine given name most famously borne by the English writer and philosopher Aldous Huxley.
-
E.
HOLLIS
HOLLIS is Harvard University's integrated online library catalog and discovery system for accessing its vast collections of books, media, and digital resources.
- 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_69a4938bdd3c8190a954a3c11844d9cf |
completed | March 1, 2026, 7:29 p.m. |
| NER | Named-entity recognition | batch_69a4ac4f740881909cb59a6c18a77af3 |
completed | March 1, 2026, 9:14 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69a7a3c1ee4481909d5713122e5ad856 |
completed | March 4, 2026, 3:15 a.m. |
| NEDg | Description generation | batch_69a7a5288338819089638d5c848735dd |
completed | March 4, 2026, 3:21 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69a7a63205308190b55b76116c0d5e7c |
completed | March 4, 2026, 3:25 a.m. |
Created at: March 1, 2026, 7:39 p.m.