Triple
T30548553
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Lady Is Willing |
E777489
|
entity |
| Predicate | hasMarleneDietrichRole |
P200818
|
FINISHED |
| Object | Liza Madden |
—
|
NE NERFINISHED |
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: Liza Madden | Statement: [The Lady Is Willing, hasMarleneDietrichRole, Liza Madden]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasMarleneDietrichRole Context triple: [The Lady Is Willing, hasMarleneDietrichRole, Liza Madden]
-
A.
hasMarleneDietrichRoleType
Indicates that an entity has a specific type or category of role associated with Marlene Dietrich.
-
B.
hasRitaHayworthRole
Indicates that an entity has a role or character associated with Rita Hayworth, such as portraying her or a role closely linked to her.
-
C.
hasGingerRogersRole
Indicates that an entity is assigned or associated with a role specifically identified as the "Ginger Rogers" role in a given context or production.
-
D.
hasJoanFontaineRole
Indicates that an entity has a role played by Joan Fontaine in a film, television, or theatrical production.
-
E.
hasBrigitteBardotRoleType
Indicates that an entity has a role type specifically associated with Brigitte Bardot (e.g., portraying her or a role category defined in relation to her).
- F. None of above. chosen
Provenance (4 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_69f2249e19108190a458ab446096bf22 |
completed | April 29, 2026, 3:32 p.m. |
| NER | Named-entity recognition | batch_69ffb1218cb08190a814c7f0833501a7 |
completed | May 9, 2026, 10:11 p.m. |
| PD | Predicate disambiguation | batch_69ffb083d6988190b2757e0cfd629b75 |
completed | May 9, 2026, 10:09 p.m. |
| PDg | Predicate description generation | batch_69ffb120b9988190b6361c69265033c0 |
completed | May 9, 2026, 10:11 p.m. |
Created at: April 29, 2026, 8:19 p.m.