Triple
T351142
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Elsa Einstein |
E7444
|
entity |
| Predicate | sibling |
P363
|
FINISHED |
| Object |
Elsa’s sister Paula
Elsa’s sister Paula was a lesser-known member of the Einstein family, related to Albert Einstein through his second wife Elsa.
|
E45006
|
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: Elsa’s sister Paula | Statement: [Elsa Einstein, sibling, Elsa’s sister Paula]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Elsa’s sister Paula Context triple: [Elsa Einstein, sibling, Elsa’s sister Paula]
-
A.
Elsa
Elsa is a feminine given name of Germanic origin, widely recognized today through its use for the main character in Disney's animated film "Frozen."
-
B.
Paula
Paula is a feminine given name used in many languages, derived from the Latin name Paulus meaning "small" or "humble."
-
C.
Mrs. Claus
Mrs. Claus is the kindly, maternal figure of Christmas folklore who lives at the North Pole with Santa, often depicted baking cookies, caring for elves, and helping manage holiday preparations.
-
D.
Hanna Lejonqvist
Hanna Lejonqvist is a film editor known for her work on the documentary "I Am Greta," which follows climate activist Greta Thunberg.
-
E.
Anna
Anna is the given first name of Eleanor Roosevelt, the influential former First Lady of the United States and human rights advocate.
- 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: Elsa’s sister Paula Triple: [Elsa Einstein, sibling, Elsa’s sister Paula]
Generated description
Elsa’s sister Paula was a lesser-known member of the Einstein family, related to Albert Einstein through his second wife Elsa.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Elsa’s sister Paula Target entity description: Elsa’s sister Paula was a lesser-known member of the Einstein family, related to Albert Einstein through his second wife Elsa.
-
A.
Elsa
Elsa is a feminine given name of Germanic origin, widely recognized today through its use for the main character in Disney's animated film "Frozen."
-
B.
Paula
Paula is a feminine given name used in many languages, derived from the Latin name Paulus meaning "small" or "humble."
-
C.
Mrs. Claus
Mrs. Claus is the kindly, maternal figure of Christmas folklore who lives at the North Pole with Santa, often depicted baking cookies, caring for elves, and helping manage holiday preparations.
-
D.
Hanna Lejonqvist
Hanna Lejonqvist is a film editor known for her work on the documentary "I Am Greta," which follows climate activist Greta Thunberg.
-
E.
Anna
Anna is the given first name of Eleanor Roosevelt, the influential former First Lady of the United States and human rights advocate.
- 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_69a2e7e696948190bebc966535995e45 |
completed | Feb. 28, 2026, 1:04 p.m. |
| NER | Named-entity recognition | batch_69a2eb7df63c8190b7cd1bcfdfd96187 |
completed | Feb. 28, 2026, 1:19 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69a3e0165b6481909345301df3f2144d |
completed | March 1, 2026, 6:43 a.m. |
| NEDg | Description generation | batch_69a3e07452388190a8162c327c76185b |
completed | March 1, 2026, 6:45 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69a3e17d43f4819081500e106d3973e9 |
completed | March 1, 2026, 6:49 a.m. |
Created at: Feb. 28, 2026, 1:08 p.m.