Triple
T3067425
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jeremy Irvine as young Eric Lomax |
E62136
|
entity |
| Predicate | sharesCharacterWith |
P44216
|
FINISHED |
| Object | Colin Firth as older Eric Lomax |
—
|
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: Colin Firth as older Eric Lomax | Statement: [Jeremy Irvine as young Eric Lomax, sharesCharacterWith, Colin Firth as older Eric Lomax]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: sharesCharacterWith Context triple: [Jeremy Irvine as young Eric Lomax, sharesCharacterWith, Colin Firth as older Eric Lomax]
-
A.
sharesElementsWith
Indicates that two entities have one or more elements or components in common.
-
B.
sharesUniverseWith
Indicates that two entities exist within the same fictional or narrative universe, implying shared continuity, setting, or canon.
-
C.
sharesFeatureWith
Indicates that two entities have at least one common attribute, property, or characteristic in common.
-
D.
sharesNameWith
Indicates that two entities have the same name or an identical naming designation.
-
E.
sharesHistoryWith
Indicates that two entities have a common or overlapping past, such as shared experiences, events, or origins.
- 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_69ad85793e5c8190a358049bc4a98d8c |
completed | March 8, 2026, 2:19 p.m. |
| NER | Named-entity recognition | batch_69ada0fea06881909e5251eea26599ac |
completed | March 8, 2026, 4:17 p.m. |
| PD | Predicate disambiguation | batch_69ad9624b7a0819091d255614f5819ea |
completed | March 8, 2026, 3:30 p.m. |
| PDg | Predicate description generation | batch_69ad97f7630c81908e1ca8a69611cff6 |
completed | March 8, 2026, 3:38 p.m. |
Created at: March 8, 2026, 3:02 p.m.