Triple
T7048433
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Law Officers of the Crown |
E163701
|
entity |
| Predicate | hasPart |
P35
|
FINISHED |
| Object |
HM Advocate
HM Advocate is the chief public prosecutor and representative of the Crown in criminal matters in Scotland.
|
E639526
|
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: HM Advocate | Statement: [Law Officers of the Crown, hasPart, HM Advocate]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: HM Advocate Context triple: [Law Officers of the Crown, hasPart, HM Advocate]
-
A.
Molly Hullis
Molly Hullis is best known as the former wife of Bee Gees singer Robin Gibb.
-
B.
Laura Harris
Laura Harris is a Canadian actress known for her roles in films like "The Faculty" and TV series such as "24" and "Dead Like Me."
-
C.
Miranda Frost
Miranda Frost is a duplicitous MI6 agent and Olympic fencer who serves as a key antagonist to James Bond in the film "Die Another Day."
-
D.
Kita Ward
Kita Ward is one of the administrative wards of Kumamoto City in Kumamoto Prefecture, Japan, functioning as a local government unit within the city.
-
E.
Meena Harris
Meena Harris is an American lawyer, author, and entrepreneur best known as the founder of the social justice–focused brand Phenomenal and for her activism on gender and racial equality.
- 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: HM Advocate Triple: [Law Officers of the Crown, hasPart, HM Advocate]
Generated description
HM Advocate is the chief public prosecutor and representative of the Crown in criminal matters in Scotland.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: HM Advocate Target entity description: HM Advocate is the chief public prosecutor and representative of the Crown in criminal matters in Scotland.
-
A.
Molly Hullis
Molly Hullis is best known as the former wife of Bee Gees singer Robin Gibb.
-
B.
Laura Harris
Laura Harris is a Canadian actress known for her roles in films like "The Faculty" and TV series such as "24" and "Dead Like Me."
-
C.
Miranda Frost
Miranda Frost is a duplicitous MI6 agent and Olympic fencer who serves as a key antagonist to James Bond in the film "Die Another Day."
-
D.
Kita Ward
Kita Ward is one of the administrative wards of Kumamoto City in Kumamoto Prefecture, Japan, functioning as a local government unit within the city.
-
E.
Meena Harris
Meena Harris is an American lawyer, author, and entrepreneur best known as the founder of the social justice–focused brand Phenomenal and for her activism on gender and racial equality.
- 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_69c6885f598c8190b6b6495c59d8d962 |
completed | March 27, 2026, 1:38 p.m. |
| NER | Named-entity recognition | batch_69c6e24c4004819086002bfe55502374 |
completed | March 27, 2026, 8:02 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c7888497b08190b1f2aa686e8e30c1 |
completed | March 28, 2026, 7:51 a.m. |
| NEDg | Description generation | batch_69c78c31d57c8190a45d25ac77ff6280 |
completed | March 28, 2026, 8:07 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69c78d635c94819083463128483a60f6 |
completed | March 28, 2026, 8:12 a.m. |
Created at: March 27, 2026, 2:37 p.m.