Triple
T26694
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Celeste Holm |
E534
|
entity |
| Predicate | performedIn |
P795
|
FINISHED |
| Object |
The Tender Trap
The Tender Trap is a 1955 romantic comedy film starring Frank Sinatra and Debbie Reynolds, adapted from the Broadway play of the same name.
|
E3521
|
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: The Tender Trap | Statement: [Celeste Holm, performedIn, The Tender Trap]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: The Tender Trap Context triple: [Celeste Holm, performedIn, The Tender Trap]
-
A.
Stumptown
Stumptown is a historic nickname for Portland, Oregon, referencing the city’s rapid 19th-century growth that left tree stumps scattered throughout the area.
-
B.
Once Again
Once Again is John Legend's Grammy-winning second studio album, known for its soulful blend of R&B, pop, and neo-soul.
-
C.
Blades the Bruin
Blades the Bruin is the official anthropomorphic bear mascot of the NHL’s Boston Bruins, known for entertaining fans at games and team events.
-
D.
Mr. Secretary
Mr. Secretary is the formal style of address traditionally used for the United States Secretary of Defense.
-
E.
Shirley
Shirley is a small town in north-central Massachusetts served by commuter rail on the MBTA Fitchburg Line.
- 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: The Tender Trap Triple: [Celeste Holm, performedIn, The Tender Trap]
Generated description
The Tender Trap is a 1955 romantic comedy film starring Frank Sinatra and Debbie Reynolds, adapted from the Broadway play of the same name.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: The Tender Trap Target entity description: The Tender Trap is a 1955 romantic comedy film starring Frank Sinatra and Debbie Reynolds, adapted from the Broadway play of the same name.
-
A.
Stumptown
Stumptown is a historic nickname for Portland, Oregon, referencing the city’s rapid 19th-century growth that left tree stumps scattered throughout the area.
-
B.
Once Again
Once Again is John Legend's Grammy-winning second studio album, known for its soulful blend of R&B, pop, and neo-soul.
-
C.
Blades the Bruin
Blades the Bruin is the official anthropomorphic bear mascot of the NHL’s Boston Bruins, known for entertaining fans at games and team events.
-
D.
Mr. Secretary
Mr. Secretary is the formal style of address traditionally used for the United States Secretary of Defense.
-
E.
Silver Star
The Silver Star is a high-level U.S. military decoration awarded for gallantry in action against an enemy of the United States.
- 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_69a243b4ac2c8190b93c303df797b7b2 |
completed | Feb. 28, 2026, 1:24 a.m. |
| NER | Named-entity recognition | batch_69a2481f9eac819093d9a950eb1ab109 |
completed | Feb. 28, 2026, 1:42 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69a24e5b531481909078feeee5cf26e2 |
completed | Feb. 28, 2026, 2:09 a.m. |
| NEDg | Description generation | batch_69a2506ad2ac8190b5a61c3fb3890d47 |
completed | Feb. 28, 2026, 2:18 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69a25147eccc8190b6151a03b064d31c |
completed | Feb. 28, 2026, 2:22 a.m. |
Created at: Feb. 28, 2026, 1:34 a.m.