Triple
T37195600
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Summer Hours |
E921581
|
entity |
| Predicate | hasMatriarchCharacter |
P9499
|
FINISHED |
| Object |
Hélène
Hélène is the elderly matriarch in the French film "Summer Hours," whose death prompts her family to confront the fate of her cherished country house and art collection.
|
E2218262
|
NE FINISHED |
How this triple was built (3 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: Hélène | Statement: [Summer Hours, hasMatriarchCharacter, Hélène]
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: Hélène Triple: [Summer Hours, hasMatriarchCharacter, Hélène]
Generated description
Hélène is the elderly matriarch in the French film "Summer Hours," whose death prompts her family to confront the fate of her cherished country house and art collection.
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasMatriarchCharacter Context triple: [Summer Hours, hasMatriarchCharacter, Hélène]
-
A.
hasMotherInLawCharacter
Indicates that one entity has the role or characteristic of being the mother-in-law of another entity.
-
B.
matriarch
chosen
Indicates that one entity holds the role or status of a female head or leading maternal figure in relation to another entity or group.
-
C.
isMaternalFigureOf
Indicates a nurturing, protective, and guiding parental-like relationship that one individual has toward another, typically in a motherly role.
-
D.
hasDomineeringMotherCharacter
Indicates that an entity is associated with a mother figure who exerts controlling, overbearing, or excessively authoritative influence over them.
-
E.
hasClanMother
Indicates that an individual belongs to or is under the authority or lineage of a specific clan mother within a clan-based social structure.
- F. None of above.
Provenance (6 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_69f76ea313a08190a54404cd1e47da90 |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_6a037c8efcd4819088c2aeead65d93df |
completed | May 12, 2026, 7:16 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a40361981c08190b818616fc341e471 |
completed | June 27, 2026, 8:44 p.m. |
| NEDg | Description generation | batch_6a40372c7dc481909314bc421b480d7e |
completed | June 27, 2026, 8:48 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a403add014081908d8f3451e59b429d |
completed | June 27, 2026, 9:04 p.m. |
| PD | Predicate disambiguation | batch_6a037a11efc08190bb7cacc1325b4dc6 |
completed | May 12, 2026, 7:05 p.m. |
Created at: May 3, 2026, 4:15 p.m.