Triple
T3629625
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Illyrians |
E76922
|
entity |
| Predicate | notableRuler |
P22
|
FINISHED |
| Object |
Teuta
Teuta was a powerful Illyrian queen of the 3rd century BCE known for her naval power and conflicts with the Roman Republic.
|
E374551
|
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: Teuta | Statement: [Illyrians, notableRuler, Teuta]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Teuta Context triple: [Illyrians, notableRuler, Teuta]
-
A.
Ariaeus
Ariaeus was a Persian military commander who served under Cyrus the Younger during his campaign against Artaxerxes II.
-
B.
Jugurtha
Jugurtha was a king of Numidia best known for his protracted war against Rome in the late 2nd century BCE, which exposed widespread corruption in the Roman Republic.
-
C.
Ahenobarbus
Ahenobarbus was the cognomen of a prominent Roman aristocratic family line to which the emperor Nero belonged.
-
D.
Armeniacus
Armeniacus was an honorific title used in ancient Rome to celebrate a military victor over Armenia, notably borne by the emperor Lucius Verus.
-
E.
Gunderic
Gunderic was a 5th-century king of the Vandals and Alans who led his people in their migration into Roman territories, laying groundwork for the Vandal kingdom later expanded by his relative Genseric.
- 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: Teuta Triple: [Illyrians, notableRuler, Teuta]
Generated description
Teuta was a powerful Illyrian queen of the 3rd century BCE known for her naval power and conflicts with the Roman Republic.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Teuta Target entity description: Teuta was a powerful Illyrian queen of the 3rd century BCE known for her naval power and conflicts with the Roman Republic.
-
A.
Ariaeus
Ariaeus was a Persian military commander who served under Cyrus the Younger during his campaign against Artaxerxes II.
-
B.
Jugurtha
Jugurtha was a king of Numidia best known for his protracted war against Rome in the late 2nd century BCE, which exposed widespread corruption in the Roman Republic.
-
C.
Ahenobarbus
Ahenobarbus was the cognomen of a prominent Roman aristocratic family line to which the emperor Nero belonged.
-
D.
Armeniacus
Armeniacus was an honorific title used in ancient Rome to celebrate a military victor over Armenia, notably borne by the emperor Lucius Verus.
-
E.
Gunderic
Gunderic was a 5th-century king of the Vandals and Alans who led his people in their migration into Roman territories, laying groundwork for the Vandal kingdom later expanded by his relative Genseric.
- 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_69ad85dc03948190b35b7189e4175bcc |
completed | March 8, 2026, 2:21 p.m. |
| NER | Named-entity recognition | batch_69adc300223881909019982ebf194f78 |
completed | March 8, 2026, 6:42 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b43328931881908bd92cb32a366e93 |
completed | March 13, 2026, 3:54 p.m. |
| NEDg | Description generation | batch_69b433a037588190a0629defe365515d |
completed | March 13, 2026, 3:56 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69b437493384819084a7213fe754526b |
completed | March 13, 2026, 4:11 p.m. |
Created at: March 8, 2026, 3:23 p.m.