Triple
T17726460
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lorelei Lee |
E442473
|
entity |
| Predicate | romanticInterest |
P7325
|
FINISHED |
| Object |
Gus Esmond
Gus Esmond is the wealthy suitor of showgirl Lorelei Lee in Anita Loos’s novel and its adaptations, "Gentlemen Prefer Blondes."
|
E1284201
|
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: Gus Esmond | Statement: [Lorelei Lee, romanticInterest, Gus Esmond]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Gus Esmond Context triple: [Lorelei Lee, romanticInterest, Gus Esmond]
-
A.
Edgar Tanner
Edgar Tanner was an Australian sports administrator best known for leading the organizing committee of the 1956 Melbourne Olympic Games.
-
B.
Rob Hilliard
Rob Hilliard is one of the main characters in the comedy film "Grown Ups," known as a quirky member of Lenny Feder’s close-knit group of childhood friends.
-
C.
Zebulon Weaver
Zebulon Weaver was an early 20th-century Democratic U.S. Representative from North Carolina who served multiple terms in Congress.
-
D.
Jesse Grimes
Jesse Grimes was a 19th-century Texas politician and early settler who played a significant role in the region’s development and governance.
-
E.
Cornelius Haggard
Cornelius Haggard is a notable individual distinguished by bearing the surname Haggard, which is associated with several prominent figures.
- 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: Gus Esmond Triple: [Lorelei Lee, romanticInterest, Gus Esmond]
Generated description
Gus Esmond is the wealthy suitor of showgirl Lorelei Lee in Anita Loos’s novel and its adaptations, "Gentlemen Prefer Blondes."
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Gus Esmond Target entity description: Gus Esmond is the wealthy suitor of showgirl Lorelei Lee in Anita Loos’s novel and its adaptations, "Gentlemen Prefer Blondes."
-
A.
Edgar Tanner
Edgar Tanner was an Australian sports administrator best known for leading the organizing committee of the 1956 Melbourne Olympic Games.
-
B.
Rob Hilliard
Rob Hilliard is one of the main characters in the comedy film "Grown Ups," known as a quirky member of Lenny Feder’s close-knit group of childhood friends.
-
C.
Zebulon Weaver
Zebulon Weaver was an early 20th-century Democratic U.S. Representative from North Carolina who served multiple terms in Congress.
-
D.
Jesse Grimes
Jesse Grimes was a 19th-century Texas politician and early settler who played a significant role in the region’s development and governance.
-
E.
Cornelius Haggard
Cornelius Haggard is a notable individual distinguished by bearing the surname Haggard, which is associated with several prominent figures.
- 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_69d8b9ec79688190b86bdcef85a7b3aa |
completed | April 10, 2026, 8:50 a.m. |
| NER | Named-entity recognition | batch_69e478e25a80819096289fba4ecb227f |
completed | April 19, 2026, 6:40 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0230324c0881909ba7b299f16b5602 |
completed | May 11, 2026, 7:38 p.m. |
| NEDg | Description generation | batch_6a0231f02cf48190ac513a7d218aca3b |
completed | May 11, 2026, 7:45 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a0233cfe9388190a7786d88a432aa1f |
completed | May 11, 2026, 7:53 p.m. |
Created at: April 10, 2026, 10:07 a.m.