Triple
T17018156
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lola |
E412873
|
entity |
| Predicate | hasCostumeDesigner |
P36430
|
FINISHED |
| Object |
Barbara Baum
Barbara Baum is a renowned German costume designer known for her work on numerous films and theater productions.
|
E1285609
|
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: Barbara Baum | Statement: [Lola, hasCostumeDesigner, Barbara Baum]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Barbara Baum Context triple: [Lola, hasCostumeDesigner, Barbara Baum]
-
A.
Barbara Heinzen
Barbara Heinzen was the wife of William Colby, the former Director of Central Intelligence of the United States.
-
B.
Barbara M. Rolph
Barbara M. Rolph was the woman who sponsored the U.S. Navy heavy cruiser USS San Francisco (CA-38) at its launching ceremony.
-
C.
Ellen Swatello
Ellen Swatello is a recurring character on the legal comedy-drama series "Franklin & Bash," portrayed as a sharp and ambitious attorney.
-
D.
Elizabeth J. Feinler
Elizabeth J. Feinler is an American information scientist best known for leading early internet directory and naming services, including managing the first WHOIS and domain name registries.
-
E.
Lorrie Baranek
Lorrie Baranek is a television producer best known for her executive production work on the current affairs series "The Problem with Jon Stewart."
- 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: Barbara Baum Triple: [Lola, hasCostumeDesigner, Barbara Baum]
Generated description
Barbara Baum is a renowned German costume designer known for her work on numerous films and theater productions.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Barbara Baum Target entity description: Barbara Baum is a renowned German costume designer known for her work on numerous films and theater productions.
-
A.
Barbara Heinzen
Barbara Heinzen was the wife of William Colby, the former Director of Central Intelligence of the United States.
-
B.
Barbara M. Rolph
Barbara M. Rolph was the woman who sponsored the U.S. Navy heavy cruiser USS San Francisco (CA-38) at its launching ceremony.
-
C.
Ellen Swatello
Ellen Swatello is a recurring character on the legal comedy-drama series "Franklin & Bash," portrayed as a sharp and ambitious attorney.
-
D.
Elizabeth J. Feinler
Elizabeth J. Feinler is an American information scientist best known for leading early internet directory and naming services, including managing the first WHOIS and domain name registries.
-
E.
Lorrie Baranek
Lorrie Baranek is a television producer best known for her executive production work on the current affairs series "The Problem with Jon Stewart."
- 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_69d886cc4170819093deddc7b8b4b6a7 |
completed | April 10, 2026, 5:12 a.m. |
| NER | Named-entity recognition | batch_69e3d480a58c8190a3912d26debb4311 |
completed | April 18, 2026, 6:59 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0242dc82dc8190a070a4d8532120fc |
completed | May 11, 2026, 8:58 p.m. |
| NEDg | Description generation | batch_6a0243ccb4f88190bc184c58e6ed0770 |
completed | May 11, 2026, 9:02 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a024426e28481909fff4f8c021e08f0 |
completed | May 11, 2026, 9:03 p.m. |
Created at: April 10, 2026, 5:33 a.m.