Triple
T9328704
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jennifer Jones |
E224461
|
entity |
| Predicate | notableWork |
P4
|
FINISHED |
| Object | Love Letters |
E241201
|
NE FINISHED |
How this triple was built (2 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: Love Letters | Statement: [Jennifer Jones, notableWork, Love Letters]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Love Letters Context triple: [Jennifer Jones, notableWork, Love Letters]
-
A.
Love Letters
chosen
Love Letters is a 1945 romantic drama film, produced by Hal B. Wallis, known for its amnesia-driven love story and Oscar-nominated screenplay by Ayn Rand.
-
B.
Love & Letter
Love & Letter is the debut full-length studio album by South Korean boy group Seventeen, showcasing their self-produced pop sound and solidifying their presence in the K-pop industry.
-
C.
The Love Letter
The Love Letter is a 1923 silent romantic drama film starring Leatrice Joy and directed by King Vidor.
-
D.
Love Letter
Love Letter is an R&B album by R. Kelly that pays homage to classic soul music with smooth, retro-inspired love songs.
-
E.
Unsent Letters
Unsent Letters is a work by British novelist and academic Malcolm Bradbury, reflecting his characteristic wit and insight into contemporary life and literature.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (3 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_69ca8427a0c08190b749831d5ea98f02 |
completed | March 30, 2026, 2:09 p.m. |
| NER | Named-entity recognition | batch_69cd37ab90ac8190b5c73f08dd091731 |
completed | April 1, 2026, 3:20 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d0c7f345d88190912b0f10e7ab68be |
completed | April 4, 2026, 8:12 a.m. |
Created at: March 30, 2026, 7:39 p.m.