Triple
T12913724
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Citadel guardians |
E308923
|
entity |
| Predicate | notablePrisonerGuarded |
P106981
|
FINISHED |
| Object | Martin Mertens |
E1010046
|
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: Martin Mertens | Statement: [Citadel guardians, notablePrisonerGuarded, Martin Mertens]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Martin Mertens Context triple: [Citadel guardians, notablePrisonerGuarded, Martin Mertens]
-
A.
Martin Mertens
chosen
Martin Mertens is a recurring Adventure Time character known as Finn the Human’s selfish and unreliable father.
-
B.
Michael Mertens
Michael Mertens is a member of the German industrial metal band Propaganda.
-
C.
Michael Mertens
Michael Mertens is a writer known for his work on the character Dr. Mabuse.
-
D.
Maximilian Merveldt
Maximilian Merveldt was an Austrian general and diplomat of the Napoleonic era, noted for his service in the wars against Revolutionary and Napoleonic France.
-
E.
Joël Scherk
Joël Scherk was a French theoretical physicist known as one of the pioneers of string theory, contributing foundational ideas to its development in the 1970s.
- 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_69d7bdf92b588190acdf2a2291ac4590 |
completed | April 9, 2026, 2:55 p.m. |
| NER | Named-entity recognition | batch_69d97dc53060819090a126f15428e411 |
completed | April 10, 2026, 10:46 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f6af5df0408190a8fe83cdd91e38c9 |
completed | May 3, 2026, 2:13 a.m. |
Created at: April 9, 2026, 5:41 p.m.