Triple
T15720699
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Pope Leo II |
E381084
|
entity |
| Predicate | birthName |
P65
|
FINISHED |
| Object |
Leo
Leo was the birth name of Pope Leo II, a 7th-century head of the Catholic Church known for confirming the acts of the Third Council of Constantinople.
|
E792059
|
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: Leo | Statement: [Pope Leo II, birthName, Leo]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Leo Context triple: [Pope Leo II, birthName, Leo]
-
A.
Leo
Leo is a zodiac constellation and astrological sign traditionally associated with the lion, symbolizing courage, leadership, and creativity.
-
B.
Leo
Leo was the given name of Leo V of Armenia, the last king of the Armenian Kingdom of Cilicia in the late 14th century.
-
C.
Leo
Leo is a central character in Noël Coward’s sophisticated stage comedy "Design for Living," embodying the play’s themes of unconventional relationships and bohemian lifestyle.
-
D.
Leo
Leo is an animated comedy film associated with Adam Sandler’s Happy Madison Productions, featuring a humorous, family-friendly story.
-
E.
Leo
Leo is a 2023 Indian Tamil-language action thriller film directed by Lokesh Kanagaraj and starring Vijay, noted for its high-octane action and connection to the Lokesh Cinematic Universe.
- 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: Leo Triple: [Pope Leo II, birthName, Leo]
Generated description
Leo was the birth name of Pope Leo II, a 7th-century head of the Catholic Church known for confirming the acts of the Third Council of Constantinople.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Leo Target entity description: Leo was the birth name of Pope Leo II, a 7th-century head of the Catholic Church known for confirming the acts of the Third Council of Constantinople.
-
A.
Leo
chosen
Leo is a masculine given name of Latin origin meaning "lion," historically borne by popes, saints, and rulers.
-
B.
Leo
Leo was the given name of Leo V of Armenia, the last king of the Armenian Kingdom of Cilicia in the late 14th century.
-
C.
Leo
Leo is a zodiac constellation and astrological sign traditionally associated with the lion, symbolizing courage, leadership, and creativity.
-
D.
Leo
Leo is the lion-themed mascot character of Japan’s professional baseball team, the Saitama Seibu Lions.
-
E.
Leo
Leo is a 2023 Indian Tamil-language action thriller film directed by Lokesh Kanagaraj and starring Vijay, noted for its high-octane action and connection to the Lokesh Cinematic Universe.
- F. None of above.
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_69d86d9bf930819082b30cf6d169297c |
completed | April 10, 2026, 3:25 a.m. |
| NER | Named-entity recognition | batch_69e04fb0b51081908e652ec4992296fa |
completed | April 16, 2026, 2:55 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ff757b7e0c81909b32aecc093c93e4 |
completed | May 9, 2026, 5:57 p.m. |
| NEDg | Description generation | batch_69ff76deb1948190bc49825719ac97d5 |
completed | May 9, 2026, 6:03 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69ff77642ba4819095c1acc65da06135 |
completed | May 9, 2026, 6:05 p.m. |
Created at: April 10, 2026, 4:45 a.m.