Triple
T15263709
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | EIP-1559 |
E364846
|
entity |
| Predicate | author |
P4
|
FINISHED |
| Object |
Eric Conner
Eric Conner is a prominent Ethereum researcher and community member known for his key role in proposing and advocating the EIP-1559 fee market upgrade.
|
E1253465
|
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: Eric Conner | Statement: [EIP-1559, author, Eric Conner]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Eric Conner Context triple: [EIP-1559, author, Eric Conner]
-
A.
Chris Conrad
Chris Conrad is a writer known for his work at the junior level, contributing developing written content and honing his craft.
-
B.
Chris Conrad
Chris Conrad is an American actor known for his roles in 1990s action and comedy films and various television series.
-
C.
Marc Connelly
Marc Connelly was an American playwright, director, and member of the Algonquin Round Table who won the Pulitzer Prize for Drama for "The Green Pastures."
-
D.
Kevin Connor
Kevin Connor is the human alter ego of the Marvel Comics superhero Starbrand, a character empowered by a cosmic energy source granting immense abilities.
-
E.
Kevin Connor
Kevin Connor is a film editor known for his work on the satirical World War I musical film "Oh! What a Lovely War."
- 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: Eric Conner Triple: [EIP-1559, author, Eric Conner]
Generated description
Eric Conner is a prominent Ethereum researcher and community member known for his key role in proposing and advocating the EIP-1559 fee market upgrade.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Eric Conner Target entity description: Eric Conner is a prominent Ethereum researcher and community member known for his key role in proposing and advocating the EIP-1559 fee market upgrade.
-
A.
Chris Conrad
Chris Conrad is an American actor known for his roles in 1990s action and comedy films and various television series.
-
B.
Chris Conrad
Chris Conrad is a writer known for his work at the junior level, contributing developing written content and honing his craft.
-
C.
Marc Connelly
Marc Connelly was an American playwright, director, and member of the Algonquin Round Table who won the Pulitzer Prize for Drama for "The Green Pastures."
-
D.
Kevin Connor
Kevin Connor is the human alter ego of the Marvel Comics superhero Starbrand, a character empowered by a cosmic energy source granting immense abilities.
-
E.
Kevin Connor
Kevin Connor is a film editor known for his work on the satirical World War I musical film "Oh! What a Lovely War."
- 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_69d85a0f08408190b3c3259ae35d79d2 |
completed | April 10, 2026, 2:01 a.m. |
| NER | Named-entity recognition | batch_69e0084fed0481908e452c89cba2be82 |
completed | April 15, 2026, 9:51 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a014819dfbc8190b39a10647f9ba64c |
completed | May 11, 2026, 3:08 a.m. |
| NEDg | Description generation | batch_6a0148d819f88190a201a31fdcd37b1c |
completed | May 11, 2026, 3:11 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a01493587948190b1a9f7ece8fcf072 |
completed | May 11, 2026, 3:12 a.m. |
Created at: April 10, 2026, 3:14 a.m.