Triple
T3668832
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Troy (film) |
E77827
|
entity |
| Predicate | characterPortrayedBy |
P1507
|
FINISHED |
| Object |
Paris – Orlando Bloom
Paris, as portrayed by Orlando Bloom, is the impulsive Trojan prince whose love affair with Helen sparks the catastrophic conflict at the heart of the epic war drama "Troy."
|
E377371
|
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: Paris – Orlando Bloom | Statement: [Troy (film), characterPortrayedBy, Paris – Orlando Bloom]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Paris – Orlando Bloom Context triple: [Troy (film), characterPortrayedBy, Paris – Orlando Bloom]
-
A.
Bray
Bray is a picturesque village on the River Thames in Berkshire, England, noted for its historic charm and renowned fine-dining restaurants.
-
B.
Langella
Langella is an Italian-origin surname most notably borne by acclaimed American actor Frank Langella.
-
C.
Chaville
Chaville is a suburban commune in the western outskirts of Paris, located in the Hauts-de-Seine department of France.
-
D.
Benoît
Benoît is the French form of the given name Benedict, commonly used in French-speaking countries.
-
E.
Jules Dormal
Jules Dormal was a Belgian-Argentine architect best known for helping complete and shape the design of Buenos Aires’ iconic Teatro Colón.
- 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: Paris – Orlando Bloom Triple: [Troy (film), characterPortrayedBy, Paris – Orlando Bloom]
Generated description
Paris, as portrayed by Orlando Bloom, is the impulsive Trojan prince whose love affair with Helen sparks the catastrophic conflict at the heart of the epic war drama "Troy."
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Paris – Orlando Bloom Target entity description: Paris, as portrayed by Orlando Bloom, is the impulsive Trojan prince whose love affair with Helen sparks the catastrophic conflict at the heart of the epic war drama "Troy."
-
A.
Bray
Bray is a picturesque village on the River Thames in Berkshire, England, noted for its historic charm and renowned fine-dining restaurants.
-
B.
Langella
Langella is an Italian-origin surname most notably borne by acclaimed American actor Frank Langella.
-
C.
Chaville
Chaville is a suburban commune in the western outskirts of Paris, located in the Hauts-de-Seine department of France.
-
D.
Benoît
Benoît is the French form of the given name Benedict, commonly used in French-speaking countries.
-
E.
Jules Dormal
Jules Dormal was a Belgian-Argentine architect best known for helping complete and shape the design of Buenos Aires’ iconic Teatro Colón.
- 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_69ad85e083008190b2e1b7085fe500bd |
completed | March 8, 2026, 2:21 p.m. |
| NER | Named-entity recognition | batch_69adc42997d88190bc765559bd7645fc |
completed | March 8, 2026, 6:47 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b4884e36108190a19887e81921fe32 |
completed | March 13, 2026, 9:57 p.m. |
| NEDg | Description generation | batch_69b48aa728fc8190b1a4e4d6d466efb5 |
completed | March 13, 2026, 10:07 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69b4af0410e8819091cb1259d06d60cc |
completed | March 14, 2026, 12:42 a.m. |
Created at: March 8, 2026, 3:25 p.m.