Triple
T17926005
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Uzi Narkiss |
E448194
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object |
Miriam Narkiss
Miriam Narkiss is best known as the wife of Israeli general Uzi Narkiss, who played a prominent role in the Six-Day War.
|
E1297088
|
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: Miriam Narkiss | Statement: [Uzi Narkiss, spouse, Miriam Narkiss]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Miriam Narkiss Context triple: [Uzi Narkiss, spouse, Miriam Narkiss]
-
A.
Miriam Palatnik
Miriam Palatnik is the mother of Brazilian kinetic and optical art pioneer Abraham Palatnik.
-
B.
Miriam Shor
Miriam Shor is an American actress best known for her television work, including her acclaimed role as Diana Trout on the comedy-drama series "Younger."
-
C.
Miriam Feirberg-Ikar
Miriam Feirberg-Ikar is an Israeli politician who has served for many years as the mayor of the coastal city of Netanya.
-
D.
Miriam Bienstock
Miriam Bienstock was an American music industry executive and co-founder of Atlantic Records who played a key role in shaping the label’s early business operations and success.
-
E.
Miriam Weinstein
Miriam Weinstein is the mother of film producer Harvey Weinstein, whose first name inspired the name of the film company Miramax.
- 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: Miriam Narkiss Triple: [Uzi Narkiss, spouse, Miriam Narkiss]
Generated description
Miriam Narkiss is best known as the wife of Israeli general Uzi Narkiss, who played a prominent role in the Six-Day War.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Miriam Narkiss Target entity description: Miriam Narkiss is best known as the wife of Israeli general Uzi Narkiss, who played a prominent role in the Six-Day War.
-
A.
Miriam Palatnik
Miriam Palatnik is the mother of Brazilian kinetic and optical art pioneer Abraham Palatnik.
-
B.
Miriam Shor
Miriam Shor is an American actress best known for her television work, including her acclaimed role as Diana Trout on the comedy-drama series "Younger."
-
C.
Miriam Feirberg-Ikar
Miriam Feirberg-Ikar is an Israeli politician who has served for many years as the mayor of the coastal city of Netanya.
-
D.
Miriam Bienstock
Miriam Bienstock was an American music industry executive and co-founder of Atlantic Records who played a key role in shaping the label’s early business operations and success.
-
E.
Miriam Weinstein
Miriam Weinstein is the mother of film producer Harvey Weinstein, whose first name inspired the name of the film company Miramax.
- 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_69d8b9f79d14819095540856928f0e25 |
completed | April 10, 2026, 8:51 a.m. |
| NER | Named-entity recognition | batch_69e4a54e03588190b36a9bb88e4085de |
completed | April 19, 2026, 9:50 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a03213465088190990a998647d8acad |
completed | May 12, 2026, 12:46 p.m. |
| NEDg | Description generation | batch_6a032338dbb48190ac0870ae5cabbb46 |
completed | May 12, 2026, 12:55 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a032435a3f08190a3c5435e4a83b0c6 |
completed | May 12, 2026, 12:59 p.m. |
Created at: April 10, 2026, 10:20 a.m.