Triple
T4745725
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Marlene Dumas |
E105356
|
entity |
| Predicate | givenName |
P17
|
FINISHED |
| Object | Marlene |
E176530
|
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: Marlene | Statement: [Marlene Dumas, givenName, Marlene]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Marlene Context triple: [Marlene Dumas, givenName, Marlene]
-
A.
Marlene
chosen
Marlene is a German biographical film directed by Joseph Vilsmaier about the life and career of actress and singer Marlene Dietrich.
-
B.
Audrey
Audrey is a kind-hearted, nature-loving girl in the 2012 animated film "The Lorax" whose dream of seeing real trees inspires the protagonist’s quest.
-
C.
Gloria
Gloria is a central human character in the 2023 film "Barbie," portrayed as a Mattel employee and mother whose personal struggles and imagination help bridge the real world with Barbie Land.
-
D.
Gloria
Gloria is an American sitcom centered on Gloria Stivic, the daughter from "All in the Family," as she navigates life as a single mother.
-
E.
Gloria
"Gloria" is a 2023 studio album by English singer-songwriter Sam Smith that explores themes of self-acceptance, love, and queer identity through pop and soul-influenced tracks.
- 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_69bd43ef87a48190a5bc3600711aa032 |
completed | March 20, 2026, 12:56 p.m. |
| NER | Named-entity recognition | batch_69bd64ab946481909eccdb3e8c5d1f6a |
completed | March 20, 2026, 3:15 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69be3a40bee88190ae97f6d409b51e96 |
completed | March 21, 2026, 6:27 a.m. |
Created at: March 20, 2026, 1:20 p.m.