Triple
T3643149
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Thracians |
E77235
|
entity |
| Predicate | worshippedDeity |
P1194
|
FINISHED |
| Object |
Bendis
Bendis is a Thracian goddess associated with the moon, hunting, and the wild, later identified with the Greek Artemis.
|
E376657
|
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: Bendis | Statement: [Thracians, worshippedDeity, Bendis]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Bendis Context triple: [Thracians, worshippedDeity, Bendis]
-
A.
Hal Foster
Hal Foster was a pioneering Canadian-American comic strip artist best known for creating and illustrating the influential adventure strip "Prince Valiant."
-
B.
Guy Gardner
Guy Gardner is a brash and headstrong member of DC Comics' Green Lantern Corps, known for his bold personality and frequent clashes with both allies and enemies.
-
C.
Adam Holender
Adam Holender is a Polish-born American cinematographer best known for shooting the influential 1969 film "Midnight Cowboy."
-
D.
Burny Mattinson
Burny Mattinson was a veteran Walt Disney animator, director, and story artist whose decades-long career contributed to many classic Disney films.
-
E.
Chris Bender
Chris Bender is a film producer known for his work on major Hollywood movies, including the thriller "Red Eye."
- 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: Bendis Triple: [Thracians, worshippedDeity, Bendis]
Generated description
Bendis is a Thracian goddess associated with the moon, hunting, and the wild, later identified with the Greek Artemis.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Bendis Target entity description: Bendis is a Thracian goddess associated with the moon, hunting, and the wild, later identified with the Greek Artemis.
-
A.
Hal Foster
Hal Foster was a pioneering Canadian-American comic strip artist best known for creating and illustrating the influential adventure strip "Prince Valiant."
-
B.
Guy Gardner
Guy Gardner is a brash and headstrong member of DC Comics' Green Lantern Corps, known for his bold personality and frequent clashes with both allies and enemies.
-
C.
Adam Holender
Adam Holender is a Polish-born American cinematographer best known for shooting the influential 1969 film "Midnight Cowboy."
-
D.
Burny Mattinson
Burny Mattinson was a veteran Walt Disney animator, director, and story artist whose decades-long career contributed to many classic Disney films.
-
E.
Chris Bender
Chris Bender is a film producer known for his work on major Hollywood movies, including the thriller "Red Eye."
- 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_69ad85de1b988190a45f8dbfebc806fc |
completed | March 8, 2026, 2:21 p.m. |
| NER | Named-entity recognition | batch_69adc35acf2c81908f60168e93b773b1 |
completed | March 8, 2026, 6:43 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b44f3207688190b8d93e2e833b15a0 |
completed | March 13, 2026, 5:53 p.m. |
| NEDg | Description generation | batch_69b453cdaae0819099c31056b7830d26 |
completed | March 13, 2026, 6:13 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69b482dfdfc08190a20e58707368b573 |
completed | March 13, 2026, 9:34 p.m. |
Created at: March 8, 2026, 3:24 p.m.