Triple
T17920996
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Locked Down |
E448064
|
entity |
| Predicate | editor |
P1954
|
FINISHED |
| Object |
Sarah Young
Sarah Young is a literary editor known for her work on the publication "Locked Down."
|
E1297225
|
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: Sarah Young | Statement: [Locked Down, editor, Sarah Young]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Sarah Young Context triple: [Locked Down, editor, Sarah Young]
-
A.
Sarah Young
Sarah Young is a virtuous young woman in Igor Stravinsky’s opera *The Rake’s Progress*, serving as the faithful beloved of the protagonist Tom Rakewell and a moral counterpoint to his downfall.
-
B.
Susan Young
Susan Young is the daughter of the fictional comedian Buddy Young Jr. from the film "Mr. Saturday Night."
-
C.
Sarah Hildreth
Sarah Hildreth was a 19th-century American stage actress who became known as the wife and political partner of U.S. senator and Civil War general Benjamin F. Butler.
-
D.
Michelle Young
Michelle Young is a reality television personality best known as the lead on season 18 of "The Bachelorette" and as a former contestant on "The Bachelor."
-
E.
Amanda Young
Amanda Young is a central character in the Saw horror film franchise, known for being one of Jigsaw’s most prominent protégés and later a conflicted antagonist.
- 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: Sarah Young Triple: [Locked Down, editor, Sarah Young]
Generated description
Sarah Young is a literary editor known for her work on the publication "Locked Down."
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Sarah Young Target entity description: Sarah Young is a literary editor known for her work on the publication "Locked Down."
-
A.
Sarah Young
Sarah Young is a virtuous young woman in Igor Stravinsky’s opera *The Rake’s Progress*, serving as the faithful beloved of the protagonist Tom Rakewell and a moral counterpoint to his downfall.
-
B.
Susan Young
Susan Young is the daughter of the fictional comedian Buddy Young Jr. from the film "Mr. Saturday Night."
-
C.
Sarah Hildreth
Sarah Hildreth was a 19th-century American stage actress who became known as the wife and political partner of U.S. senator and Civil War general Benjamin F. Butler.
-
D.
Michelle Young
Michelle Young is a reality television personality best known as the lead on season 18 of "The Bachelorette" and as a former contestant on "The Bachelor."
-
E.
Amanda Young
Amanda Young is a central character in the Saw horror film franchise, known for being one of Jigsaw’s most prominent protégés and later a conflicted antagonist.
- 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_69d8b9f6d394819082a6d69fd1e23d2f |
completed | April 10, 2026, 8:51 a.m. |
| NER | Named-entity recognition | batch_69e4a30a11748190be41361d108aee58 |
completed | April 19, 2026, 9:40 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a032130dc1c819082168b89a41043e2 |
completed | May 12, 2026, 12:46 p.m. |
| NEDg | Description generation | batch_6a0325567708819081ede6f64fec5035 |
completed | May 12, 2026, 1:04 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a03268624308190b80666dbcc527619 |
completed | May 12, 2026, 1:09 p.m. |
Created at: April 10, 2026, 10:20 a.m.