Triple
T33818154
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Garry Lejeune |
E866747
|
entity |
| Predicate | roleInNothingOn |
P164462
|
FINISHED |
| Object |
Roger Tramplemain
Roger Tramplemain is a fictional character in Michael Frayn's farce "Noises Off," appearing as the suave, somewhat hapless lead in the play-within-the-play.
|
E2070297
|
NE FINISHED |
How this triple was built (3 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: Roger Tramplemain | Statement: [Garry Lejeune, roleInNothingOn, Roger Tramplemain]
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: Roger Tramplemain Triple: [Garry Lejeune, roleInNothingOn, Roger Tramplemain]
Generated description
Roger Tramplemain is a fictional character in Michael Frayn's farce "Noises Off," appearing as the suave, somewhat hapless lead in the play-within-the-play.
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: roleInNothingOn Context triple: [Garry Lejeune, roleInNothingOn, Roger Tramplemain]
-
A.
roleInNobody
Indicates that an entity has a specific role or function within the context of the work titled "Nobody" (e.g., a film, book, or other creative work named "Nobody").
-
B.
roleInCons
Indicates that an entity holds a specific role or function within a particular consortium.
-
C.
nonRole
chosen
Indicates that the specified entity does not hold, perform, or belong to the given role within the described context.
-
D.
roleInSilhouette
Indicates that an entity has a specific functional or positional role within a larger silhouette or outline structure.
-
E.
otherRole
Indicates that an entity holds an additional or alternative role in relation to another entity, distinct from its primary role.
- F. None of above.
Provenance (6 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_69f349911a8c81908478662194b23d8c |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_6a00a846a8f881908b073ad13a5af6ca |
completed | May 10, 2026, 3:46 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a366e9cb9008190ab758e77985575e5 |
completed | June 20, 2026, 10:42 a.m. |
| NEDg | Description generation | batch_6a367027c6c8819082ff0adde1304ee4 |
completed | June 20, 2026, 10:49 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a36710b582c8190a9510e1ab6c5d1e0 |
completed | June 20, 2026, 10:52 a.m. |
| PD | Predicate disambiguation | batch_6a00a7aae194819085e1a2fd406f7922 |
completed | May 10, 2026, 3:43 p.m. |
Created at: May 1, 2026, 1:46 a.m.