Triple
T18289736
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Man Who Came Back (1924 film) |
E438079
|
entity |
| Predicate | basedOnAuthor |
P2806
|
FINISHED |
| Object |
Eugene Walter
Eugene Walter was an American playwright and screenwriter known for his popular early 20th-century stage dramas that were frequently adapted into films.
|
E1385407
|
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: Eugene Walter | Statement: [The Man Who Came Back (1924 film), basedOnAuthor, Eugene Walter]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Eugene Walter Context triple: [The Man Who Came Back (1924 film), basedOnAuthor, Eugene Walter]
-
A.
Eugene Maurice
Eugene Maurice was a 17th-century French nobleman and military commander who held the title of Count of Soissons.
-
B.
Eugene Isaac
Eugene Isaac is the son of Guatemalan-American actor Oscar Isaac.
-
C.
Eugene Fitzherbert
Eugene Fitzherbert is the charming, roguish thief-turned-hero from Disney's animated film "Tangled," better known by his alias Flynn Rider.
-
D.
John Carl Buechler
John Carl Buechler was an American special effects artist, makeup designer, and film director known for his creature effects work on numerous 1980s and 1990s horror and fantasy films.
-
E.
Eugene Corr
Eugene Corr is an American screenwriter and filmmaker known for his work on socially conscious films and documentaries.
- 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: Eugene Walter Triple: [The Man Who Came Back (1924 film), basedOnAuthor, Eugene Walter]
Generated description
Eugene Walter was an American playwright and screenwriter known for his popular early 20th-century stage dramas that were frequently adapted into films.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Eugene Walter Target entity description: Eugene Walter was an American playwright and screenwriter known for his popular early 20th-century stage dramas that were frequently adapted into films.
-
A.
Eugene Maurice
Eugene Maurice was a 17th-century French nobleman and military commander who held the title of Count of Soissons.
-
B.
Eugene Isaac
Eugene Isaac is the son of Guatemalan-American actor Oscar Isaac.
-
C.
Eugene Fitzherbert
Eugene Fitzherbert is the charming, roguish thief-turned-hero from Disney's animated film "Tangled," better known by his alias Flynn Rider.
-
D.
John Carl Buechler
John Carl Buechler was an American special effects artist, makeup designer, and film director known for his creature effects work on numerous 1980s and 1990s horror and fantasy films.
-
E.
Eugene Corr
Eugene Corr is an American screenwriter and filmmaker known for his work on socially conscious films and documentaries.
- 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_69d8b914530c8190b4474d862a2b2a1b |
completed | April 10, 2026, 8:47 a.m. |
| NER | Named-entity recognition | batch_69e500fd65888190afdbb29dc60066af |
completed | April 19, 2026, 4:21 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a075ef474d48190a781d81f02ec4886 |
completed | May 15, 2026, 5:59 p.m. |
| NEDg | Description generation | batch_6a076088e1008190bc21398053607d24 |
completed | May 15, 2026, 6:06 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a0760e165b88190bf8d7712b073cdd8 |
completed | May 15, 2026, 6:07 p.m. |
Created at: April 10, 2026, 10:35 a.m.