Triple
T15108381
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 10gen |
E360846
|
entity |
| Predicate | foundedBy |
P104
|
FINISHED |
| Object | Dwight Merriman |
E73517
|
NE FINISHED |
How this triple was built (2 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: Dwight Merriman | Statement: [10gen, foundedBy, Dwight Merriman]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Dwight Merriman Context triple: [10gen, foundedBy, Dwight Merriman]
-
A.
Dwight Merriman
chosen
Dwight Merriman is an American entrepreneur and technologist best known as a co-founder of DoubleClick and later MongoDB.
-
B.
Dwight McClusky
Dwight McClusky is a brash, sensationalist television journalist and talk-show host in the satirical crime film "Natural Born Killers."
-
C.
Dwight Walker
Dwight Walker is the birth name of Lucious Lyon, the ambitious and ruthless music mogul at the center of the television series "Empire."
-
D.
Dwight White
Dwight White was a standout defensive end for the Pittsburgh Steelers, best known as a key member of their dominant 1970s "Steel Curtain" defense that helped the team win multiple Super Bowls.
-
E.
Bil Dwyer
Bil Dwyer is an American stand-up comedian and television game show host known for his quick wit and work on various comedy and reality-based programs.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (3 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_69d85a0491ec8190830960be8fafb994 |
completed | April 10, 2026, 2:01 a.m. |
| NER | Named-entity recognition | batch_69e0058af8988190977d998f85893836 |
completed | April 15, 2026, 9:39 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a004f3548b48190aec852723654bd35 |
completed | May 10, 2026, 9:26 a.m. |
Created at: April 10, 2026, 3:05 a.m.