Triple
T22505870
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Aaron Hill |
E556386
|
entity |
| Predicate | hasChild |
P369
|
FINISHED |
| Object |
Elizabeth Hill
Elizabeth Hill is known primarily as the daughter of English dramatist and poet Aaron Hill.
|
E1569411
|
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: Elizabeth Hill | Statement: [Aaron Hill, hasChild, Elizabeth Hill]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Elizabeth Hill Context triple: [Aaron Hill, hasChild, Elizabeth Hill]
-
A.
Elizabeth Hill
Elizabeth Hill was the wife of acclaimed American film director King Vidor, associated with Hollywood's classic era.
-
B.
Elizabeth Hill
Elizabeth Hill was a screenwriter known for her work on the film "Our Daily Bread."
-
C.
Rachel Hill
Rachel Hill is an American professional soccer forward known for her time with the Chicago Red Stars in the National Women's Soccer League.
-
D.
Emma Hill
Emma Hill is a central character in the psychological thriller TV series "The Following," known for her role within the show's cult-driven narrative.
-
E.
Emma Hill
Emma Hill is a central figure portrayed in Ford Madox Brown’s painting "The Last of England," serving as the model for the emigrant wife in this iconic Victorian artwork.
- 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: Elizabeth Hill Triple: [Aaron Hill, hasChild, Elizabeth Hill]
Generated description
Elizabeth Hill is known primarily as the daughter of English dramatist and poet Aaron Hill.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Elizabeth Hill Target entity description: Elizabeth Hill is known primarily as the daughter of English dramatist and poet Aaron Hill.
-
A.
Elizabeth Hill
Elizabeth Hill was the wife of acclaimed American film director King Vidor, associated with Hollywood's classic era.
-
B.
Elizabeth Hill
Elizabeth Hill was a screenwriter known for her work on the film "Our Daily Bread."
-
C.
Rachel Hill
Rachel Hill is an American professional soccer forward known for her time with the Chicago Red Stars in the National Women's Soccer League.
-
D.
Emma Hill
Emma Hill is a central character in the psychological thriller TV series "The Following," known for her role within the show's cult-driven narrative.
-
E.
Emma Hill
Emma Hill is a central figure portrayed in Ford Madox Brown’s painting "The Last of England," serving as the model for the emigrant wife in this iconic Victorian artwork.
- 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_69e11e555edc81909ca803587dafd747 |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f15d5bf0f0819093426d83ebd80ef0 |
completed | April 29, 2026, 1:22 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0c1591515c8190a452c6270d0a9aef |
completed | May 19, 2026, 7:47 a.m. |
| NEDg | Description generation | batch_6a0c17e68aac8190889632ca941b5567 |
completed | May 19, 2026, 7:57 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a0c18722a2c81908dab6d620bdc3afe |
completed | May 19, 2026, 7:59 a.m. |
Created at: April 16, 2026, 8:50 p.m.