Triple
T36670229
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Curious Case of Benjamin Button |
E905390
|
entity |
| Predicate | protagonistBirthForm |
P186150
|
FINISHED |
| Object | old man |
—
|
LITERAL FINISHED |
How this triple was built (2 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: old man | Statement: [The Curious Case of Benjamin Button, protagonistBirthForm, old man]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: protagonistBirthForm Context triple: [The Curious Case of Benjamin Button, protagonistBirthForm, old man]
-
A.
protagonistOrigin
Indicates that one entity is the origin, source, or starting point of the protagonist in a narrative or story.
-
B.
protagonistSpecies
Indicates that an entity is the species or kind of creature to which the protagonist of a story or scenario belongs.
-
C.
protagonistType
Indicates the role or category that the main character (protagonist) of a story or scenario belongs to.
-
D.
protagonistRaisedBy
Indicates that one entity serves as the primary caregiver or guardian who brings up, nurtures, and looks after the other entity during their formative years.
-
E.
protagonistBasedOn
Indicates that a fictional work’s main character is modeled on, inspired by, or derived from a particular real or fictional person or entity.
- F. None of above. chosen
Provenance (4 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_69f76e6f10008190aea41746aa1b186e |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_69f7c83f5960819089610ed39c839678 |
completed | May 3, 2026, 10:12 p.m. |
| PD | Predicate disambiguation | batch_69f7c4796ebc819084a0dc08505e5f14 |
completed | May 3, 2026, 9:56 p.m. |
| PDg | Predicate description generation | batch_69f7c776b4088190bef550c869da530d |
completed | May 3, 2026, 10:08 p.m. |
Created at: May 3, 2026, 4:12 p.m.