Triple
T21051184
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kevin Hartz |
E518585
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object |
Julia Hartz
Julia Hartz is an American entrepreneur and co-founder/CEO of Eventbrite, a major global ticketing and event management platform.
|
E1465780
|
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: Julia Hartz | Statement: [Kevin Hartz, spouse, Julia Hartz]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Julia Hartz Context triple: [Kevin Hartz, spouse, Julia Hartz]
-
A.
Lissy Gerhardt
Lissy Gerhardt is a fictional character known primarily as the daughter of Marine Gunnery Sergeant Mack Gerhardt in the military drama series "Over There."
-
B.
Alexandra Behrs
Alexandra Behrs was a member of the Behrs family and a sister of Sofya Andreyevna Behrs, the wife of Russian writer Leo Tolstoy.
-
C.
Rebecca Otto
Rebecca Otto is an American politician and former Minnesota State Auditor known for her work on government accountability and fiscal oversight.
-
D.
Heidi von Palleske
Heidi von Palleske is a Canadian actress and writer best known for her role in David Cronenberg’s psychological horror film "Dead Ringers."
-
E.
Julia Sebestyen
Júlia Sebestyén is a Hungarian former competitive figure skater best known for winning the 2004 European Championship and competing in multiple Winter Olympics.
- 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: Julia Hartz Triple: [Kevin Hartz, spouse, Julia Hartz]
Generated description
Julia Hartz is an American entrepreneur and co-founder/CEO of Eventbrite, a major global ticketing and event management platform.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Julia Hartz Target entity description: Julia Hartz is an American entrepreneur and co-founder/CEO of Eventbrite, a major global ticketing and event management platform.
-
A.
Lissy Gerhardt
Lissy Gerhardt is a fictional character known primarily as the daughter of Marine Gunnery Sergeant Mack Gerhardt in the military drama series "Over There."
-
B.
Alexandra Behrs
Alexandra Behrs was a member of the Behrs family and a sister of Sofya Andreyevna Behrs, the wife of Russian writer Leo Tolstoy.
-
C.
Rebecca Otto
Rebecca Otto is an American politician and former Minnesota State Auditor known for her work on government accountability and fiscal oversight.
-
D.
Heidi von Palleske
Heidi von Palleske is a Canadian actress and writer best known for her role in David Cronenberg’s psychological horror film "Dead Ringers."
-
E.
Julia Sebestyen
Júlia Sebestyén is a Hungarian former competitive figure skater best known for winning the 2004 European Championship and competing in multiple Winter Olympics.
- 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_69e0b5053ac48190921529544959e906 |
completed | April 16, 2026, 10:08 a.m. |
| NER | Named-entity recognition | batch_69e6fd7bd96c81909cb46419ad4e1222 |
completed | April 21, 2026, 4:30 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a095a4bf5048190867f67140395a045 |
completed | May 17, 2026, 6:03 a.m. |
| NEDg | Description generation | batch_6a095b1cb97c8190b3ba95373bd21056 |
completed | May 17, 2026, 6:07 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a095bf3efa4819089368a3e80a41e15 |
completed | May 17, 2026, 6:11 a.m. |
Created at: April 16, 2026, 2:35 p.m.