Triple
T21859023
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | George Ignatieff |
E539709
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object |
Alison Grant
Alison Grant was the wife of Canadian diplomat and academic George Ignatieff, associated with his prominent public and intellectual life.
|
E1546621
|
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: Alison Grant | Statement: [George Ignatieff, spouse, Alison Grant]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Alison Grant Context triple: [George Ignatieff, spouse, Alison Grant]
-
A.
Alison Gordon
Alison Gordon is a fictional character from the "Saw" horror film franchise, known as the wife of Dr. Lawrence Gordon and a victim in Jigsaw’s deadly games.
-
B.
Alison Owen
Alison Owen is a British film producer known for acclaimed works such as "Elizabeth," "Shaun of the Dead," and "Saving Mr. Banks."
-
C.
Alison McDonald
Alison McDonald is a television writer and producer known for her work on series such as "Russian Doll" and "Annie."
-
D.
Alison Scott
Alison Scott is the ambitious entertainment journalist and unexpected mother-to-be portrayed by Katherine Heigl in the 2007 comedy film "Knocked Up."
-
E.
Alison Woods
Alison Woods is an American actress best known for her role in the horror-comedy film "Detention."
- 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: Alison Grant Triple: [George Ignatieff, spouse, Alison Grant]
Generated description
Alison Grant was the wife of Canadian diplomat and academic George Ignatieff, associated with his prominent public and intellectual life.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Alison Grant Target entity description: Alison Grant was the wife of Canadian diplomat and academic George Ignatieff, associated with his prominent public and intellectual life.
-
A.
Alison Gordon
Alison Gordon is a fictional character from the "Saw" horror film franchise, known as the wife of Dr. Lawrence Gordon and a victim in Jigsaw’s deadly games.
-
B.
Alison Owen
Alison Owen is a British film producer known for acclaimed works such as "Elizabeth," "Shaun of the Dead," and "Saving Mr. Banks."
-
C.
Alison McDonald
Alison McDonald is a television writer and producer known for her work on series such as "Russian Doll" and "Annie."
-
D.
Alison Scott
Alison Scott is the ambitious entertainment journalist and unexpected mother-to-be portrayed by Katherine Heigl in the 2007 comedy film "Knocked Up."
-
E.
Alison Woods
Alison Woods is an American actress best known for her role in the horror-comedy film "Detention."
- 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_69e0c47829648190bbe2d1d7033768ec |
completed | April 16, 2026, 11:14 a.m. |
| NER | Named-entity recognition | batch_69f0d63944d88190b6bd5e6ba4cc8ec1 |
completed | April 28, 2026, 3:46 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0b4de30fb48190b2c0961e8f50f6c6 |
completed | May 18, 2026, 5:35 p.m. |
| NEDg | Description generation | batch_6a0b50ca48648190806c5c4af619d1d6 |
completed | May 18, 2026, 5:47 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a0b515b7350819081c9f3a5103687eb |
completed | May 18, 2026, 5:50 p.m. |
Created at: April 16, 2026, 6:56 p.m.