Triple
T33590797
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tango (por una cabeza) |
E860412
|
entity |
| Predicate | hasRefrainPhrase |
P85363
|
FINISHED |
| Object | Por una cabeza |
E965739
|
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: Por una cabeza | Statement: [Tango (por una cabeza), hasRefrainPhrase, Por una cabeza]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasRefrainPhrase Context triple: [Tango (por una cabeza), hasRefrainPhrase, Por una cabeza]
-
A.
hasRefrainRelatedTo
Indicates that a refrain (repeated musical or textual section) in one work is thematically or content-wise related to another specified subject or element.
-
B.
hasRefrainFunction
Indicates that something serves the role or function of a refrain, typically recurring in a structured or repetitive way within a larger context.
-
C.
hasLyricPhrase
chosen
Indicates that one entity (typically a song or musical work) contains or is associated with a specific lyric phrase as part of its textual content.
-
D.
containsRefrainAlsoFoundIn
Indicates that one entity includes a refrain that is also present in another entity.
-
E.
refrainCount
Indicates the number of times a particular refrain or repeated segment occurs within a larger sequence or structure.
- F. None of above.
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_69f3497e70e48190951c94d072879bec |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_6a037c8ae0248190b7e2ce4bf852c22d |
completed | May 12, 2026, 7:16 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a361191ced08190a6c8bf2f5b52d208 |
completed | June 20, 2026, 4:05 a.m. |
| PD | Predicate disambiguation | batch_6a0379f505c88190ac0879ab422c3054 |
completed | May 12, 2026, 7:05 p.m. |
Created at: May 1, 2026, 1:40 a.m.