Triple
T25993345
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dragan Dabić |
E646418
|
entity |
| Predicate | realIdentityName |
P9233
|
FINISHED |
| Object | Radovan Karadžić |
—
|
NE NERFINISHED |
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: Radovan Karadžić | Statement: [Dragan Dabić, realIdentityName, Radovan Karadžić]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: realIdentityName Context triple: [Dragan Dabić, realIdentityName, Radovan Karadžić]
-
A.
realName
chosen
Indicates that one entity is the actual, full, or birth name of another entity, which may be known by an alias, nickname, or alternate identity.
-
B.
publicIdentity
Indicates that an entity’s outward-facing identity or persona is known, presented, or recognized in a public context.
-
C.
notRealNameOf
Indicates that the referenced name is not the entity’s actual or official name (e.g., it is false, fabricated, or otherwise not the real name of that entity).
-
D.
originalIdentity
Indicates that one entity represents the initial or true identity from which another entity is derived, transformed, or aliased.
-
E.
fullNameRevealed
Indicates that an entity’s complete personal name has been disclosed or made known to another party or in a given context.
- F. None of above.
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_69e77e88cb8481908da31d4a00661f55 |
completed | April 21, 2026, 1:41 p.m. |
| NER | Named-entity recognition | batch_69f60549019c81909fb687c81d9ac27d |
completed | May 2, 2026, 2:08 p.m. |
| PD | Predicate disambiguation | batch_69f5f7fba5248190945acf1561280799 |
completed | May 2, 2026, 1:11 p.m. |
Created at: April 22, 2026, 8:57 a.m.