Triple
T28431874
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Amy Forrest-Rhodes |
E715153
|
entity |
| Predicate | spouseRoleInNotableWork |
P161452
|
FINISHED |
| Object |
Clarence Odbody, the angel
Clarence Odbody is the bumbling yet kind-hearted guardian angel in the classic film "It's a Wonderful Life," sent to help George Bailey by showing him the value of his own existence.
|
E1818187
|
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: Clarence Odbody, the angel | Statement: [Amy Forrest-Rhodes, spouseRoleInNotableWork, Clarence Odbody, the angel]
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: Clarence Odbody, the angel Triple: [Amy Forrest-Rhodes, spouseRoleInNotableWork, Clarence Odbody, the angel]
Generated description
Clarence Odbody is the bumbling yet kind-hearted guardian angel in the classic film "It's a Wonderful Life," sent to help George Bailey by showing him the value of his own existence.
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: spouseRoleInNotableWork Context triple: [Amy Forrest-Rhodes, spouseRoleInNotableWork, Clarence Odbody, the angel]
-
A.
spouseNotableWorkField
Indicates that the notable work or professional field associated with a person’s spouse is being specified.
-
B.
spouse notableWork
chosen
Indicates that a person's spouse is significantly associated with a particular notable work.
-
C.
spouseNotableFor
Indicates that a person's spouse is recognized or distinguished for a particular achievement, role, or characteristic.
-
D.
spouseOfRole
Indicates that one role is the spouse (husband, wife, or equivalent marital partner) of another role.
-
E.
spouseNotableWorkLanguage
Indicates that the notable work of a person's spouse is expressed or created in a particular language.
- 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_69efd6b253888190b3c7222ed6a403a8 |
completed | April 27, 2026, 9:35 p.m. |
| NER | Named-entity recognition | batch_69f73223675481908c1bc3208c0f5284 |
completed | May 3, 2026, 11:31 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a163326778c81908ddc3cd63657bee2 |
completed | May 26, 2026, 11:56 p.m. |
| NEDg | Description generation | batch_6a1634d732108190879d926709565d61 |
completed | May 27, 2026, 12:03 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a1637f2c5288190a0dedce173d7e17e |
completed | May 27, 2026, 12:16 a.m. |
| PD | Predicate disambiguation | batch_69f7317690108190b3aae2cd2e1d069e |
completed | May 3, 2026, 11:28 a.m. |
Created at: April 28, 2026, 1:40 a.m.