Triple
T11859540
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Eva Amurri |
E282122
|
entity |
| Predicate | notableWork |
P4
|
FINISHED |
| Object | Animals |
E779258
|
NE 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: Animals | Statement: [Eva Amurri, notableWork, Animals]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Animals Context triple: [Eva Amurri, notableWork, Animals]
-
A.
Animals
chosen
Animals is a 2019 independent drama film exploring the hedonistic yet strained friendship between two women in Dublin, starring Holliday Grainger.
-
B.
Animals
Animals is a 1977 concept album by Pink Floyd, largely created by Roger Waters, that presents a dark, politically charged critique of society through extended progressive rock compositions.
-
C.
Animals
"Animals" is a 2013 big-room house track by Dutch DJ and producer Martin Garrix that became an international hit and a defining anthem of the EDM festival era.
-
D.
Animals
"Animals" is a 1941 modernist painting by Mexican artist Rufino Tamayo that depicts stylized, expressive creatures in a vivid, semi-abstract composition.
-
E.
Dieren
Dieren is a village in the Dutch province of Gelderland, known as a gateway to the Veluwezoom National Park and the surrounding wooded and river landscapes.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (3 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_69d6ab287ba48190a5178779fd19b9b7 |
completed | April 8, 2026, 7:23 p.m. |
| NER | Named-entity recognition | batch_69d8a69a099c8190a674db64c50eca5a |
completed | April 10, 2026, 7:28 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f281745ca88190968e1f674d0e483c |
completed | April 29, 2026, 10:08 p.m. |
Created at: April 8, 2026, 9:43 p.m.