Triple
T21081777
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Wójcicki |
E519386
|
entity |
| Predicate | hasNotableBearer |
P458
|
FINISHED |
| Object |
Jan Wójcik
Jan Wójcik is a Polish individual notable primarily for bearing the surname Wójcicki.
|
E1489881
|
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: Jan Wójcik | Statement: [Wójcicki, hasNotableBearer, Jan Wójcik]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Jan Wójcik Context triple: [Wójcicki, hasNotableBearer, Jan Wójcik]
-
A.
Tom Jankiewicz
Tom Jankiewicz was an American screenwriter best known for writing the cult dark comedy film "Grosse Pointe Blank."
-
B.
Maciej Stuhr
Maciej Stuhr is a Polish actor and comedian known for his film, television, and theater roles as well as his work as a satirist and public figure.
-
C.
John Wolyniec
John Wolyniec is a former American professional soccer forward best known for his time with the New York/New Jersey MetroStars and New York Red Bulls in Major League Soccer.
-
D.
Filip Wolski
Filip Wolski is a machine learning researcher known for his work at OpenAI, including contributions to reinforcement learning methods such as Proximal Policy Optimization (PPO).
-
E.
Marek Piekarski
Marek Piekarski is a Polish former footballer known for playing as a midfielder in the 1970s and 1980s.
- 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: Jan Wójcik Triple: [Wójcicki, hasNotableBearer, Jan Wójcik]
Generated description
Jan Wójcik is a Polish individual notable primarily for bearing the surname Wójcicki.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Jan Wójcik Target entity description: Jan Wójcik is a Polish individual notable primarily for bearing the surname Wójcicki.
-
A.
Tom Jankiewicz
Tom Jankiewicz was an American screenwriter best known for writing the cult dark comedy film "Grosse Pointe Blank."
-
B.
Maciej Stuhr
Maciej Stuhr is a Polish actor and comedian known for his film, television, and theater roles as well as his work as a satirist and public figure.
-
C.
John Wolyniec
John Wolyniec is a former American professional soccer forward best known for his time with the New York/New Jersey MetroStars and New York Red Bulls in Major League Soccer.
-
D.
Filip Wolski
Filip Wolski is a machine learning researcher known for his work at OpenAI, including contributions to reinforcement learning methods such as Proximal Policy Optimization (PPO).
-
E.
Marek Piekarski
Marek Piekarski is a Polish former footballer known for playing as a midfielder in the 1970s and 1980s.
- 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_69e0b506e59c8190849b71ed07929215 |
completed | April 16, 2026, 10:08 a.m. |
| NER | Named-entity recognition | batch_69e702db430c81908a1547d8fbe45506 |
completed | April 21, 2026, 4:53 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a09eec761288190903bf3d4f02908f2 |
completed | May 17, 2026, 4:37 p.m. |
| NEDg | Description generation | batch_6a09efd967d481909c9e0bc1c3f18f4a |
completed | May 17, 2026, 4:42 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a09f06905108190b77d5bd95f261f3b |
completed | May 17, 2026, 4:44 p.m. |
Created at: April 16, 2026, 2:49 p.m.