Triple
T14412209
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Pablo Berger |
E357356
|
entity |
| Predicate | directed |
P7373
|
FINISHED |
| Object | Abracadabra |
E357353
|
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: Abracadabra | Statement: [Pablo Berger, directed, Abracadabra]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Abracadabra Context triple: [Pablo Berger, directed, Abracadabra]
-
A.
Abracadabra
chosen
Abracadabra is a 2017 Spanish dark comedy film that blends elements of fantasy and psychological drama, directed by Pablo Berger and starring Maribel Verdú.
-
B.
Abracadabra
"Abracadabra" is a 1982 hit rock song by the Steve Miller Band, known for its catchy chorus and prominent use of synthesizers.
-
C.
Abracadabra
"Abracadabra" is a 1991 studio album by English singer Martin Fry's band ABC, showcasing their polished pop sound and sophisticated production.
-
D.
Magicians
Magicians is a British comedy film that follows two feuding stage magicians whose rivalry leads to increasingly absurd and disastrous performances.
-
E.
Encants
Encants is a Barcelona Metro station on Line 2 serving the Eixample district near the historic Encants flea market.
- 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_69d82793421c8190861eb0e673b085de |
completed | April 9, 2026, 10:26 p.m. |
| NER | Named-entity recognition | batch_69de90cb3c708190822f5506ebf7ee9d |
completed | April 14, 2026, 7:08 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fd5bc79c088190b6fd2984515976d7 |
completed | May 8, 2026, 3:43 a.m. |
Created at: April 10, 2026, 1:17 a.m.