Triple
T6559149
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | David Nelson |
E152530
|
entity |
| Predicate | child |
P120
|
FINISHED |
| Object | Gunnar Nelson |
E4078
|
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: Gunnar Nelson | Statement: [David Nelson, child, Gunnar Nelson]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Gunnar Nelson Context triple: [David Nelson, child, Gunnar Nelson]
-
A.
Gunnar Nelson
chosen
Gunnar Nelson is an Icelandic mixed martial artist and Brazilian jiu-jitsu specialist known for his grappling-focused fighting style in the UFC.
-
B.
Ben Askren
Ben Askren is a retired American mixed martial artist and former Olympic wrestler known for his elite grappling and championship runs in Bellator and ONE Championship.
-
C.
Rafael dos Anjos
Rafael dos Anjos is a Brazilian mixed martial artist and former UFC lightweight champion known for his high-pressure striking and well-rounded grappling.
-
D.
Donald Cerrone
Donald Cerrone is an American mixed martial artist and kickboxer known for his prolific UFC career, fan-friendly fighting style, and record number of appearances and bonuses in the promotion.
-
E.
Michael Chandler
Michael Chandler is a film editor known for his work on notable movies including the acclaimed drama "Amadeus."
- 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_69c688058d6881908c19b309cc55dbfa |
completed | March 27, 2026, 1:37 p.m. |
| NER | Named-entity recognition | batch_69c6ae202e508190a08a0c0584648b83 |
completed | March 27, 2026, 4:19 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c6d55c817481908f570b85a6b407f9 |
completed | March 27, 2026, 7:07 p.m. |
Created at: March 27, 2026, 1:52 p.m.