Triple
T18148033
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Come Undone |
E434436
|
entity |
| Predicate | writer |
P1360
|
FINISHED |
| Object |
Daniel Pierre
Daniel Pierre is a songwriter best known for co-writing the song "Come Undone."
|
E1308230
|
NE FINISHED |
How this triple was built (4 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: Daniel Pierre | Statement: [Come Undone, writer, Daniel Pierre]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Daniel Pierre Context triple: [Come Undone, writer, Daniel Pierre]
-
A.
Pierre Michel
Pierre Michel is a minor but pivotal character in Agatha Christie's detective novel "Murder on the Orient Express," serving as the train's conductor and playing a key role in the mystery surrounding the central crime.
-
B.
Boris Dilliès
Boris Dilliès is a Belgian politician known for serving as the mayor of the Brussels municipality of Uccle.
-
C.
François-Xavier Roth
François-Xavier Roth is a French conductor renowned for his innovative programming, historically informed performances, and leadership of ensembles such as Les Siècles and major international orchestras.
-
D.
Philippe Pemezec
Philippe Pemezec is a French politician known for serving as mayor of the Parisian suburb Le Plessis-Robinson.
-
E.
Jean-François Dieterich
Jean-François Dieterich is a French local politician serving as the mayor of the Mediterranean coastal commune of Saint-Jean-Cap-Ferrat.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Daniel Pierre Triple: [Come Undone, writer, Daniel Pierre]
Generated description
Daniel Pierre is a songwriter best known for co-writing the song "Come Undone."
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Daniel Pierre Target entity description: Daniel Pierre is a songwriter best known for co-writing the song "Come Undone."
-
A.
Pierre Michel
Pierre Michel is a minor but pivotal character in Agatha Christie's detective novel "Murder on the Orient Express," serving as the train's conductor and playing a key role in the mystery surrounding the central crime.
-
B.
Boris Dilliès
Boris Dilliès is a Belgian politician known for serving as the mayor of the Brussels municipality of Uccle.
-
C.
François-Xavier Roth
François-Xavier Roth is a French conductor renowned for his innovative programming, historically informed performances, and leadership of ensembles such as Les Siècles and major international orchestras.
-
D.
Philippe Pemezec
Philippe Pemezec is a French politician known for serving as mayor of the Parisian suburb Le Plessis-Robinson.
-
E.
Jean-François Dieterich
Jean-François Dieterich is a French local politician serving as the mayor of the Mediterranean coastal commune of Saint-Jean-Cap-Ferrat.
- F. None of above. chosen
Provenance (5 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_69d8b90aac308190801e2c57d8c5bfe5 |
completed | April 10, 2026, 8:47 a.m. |
| NER | Named-entity recognition | batch_69e4de360ae88190abe1ed13243e9924 |
completed | April 19, 2026, 1:52 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a03855631f48190ae8c343a4fa8f2a6 |
completed | May 12, 2026, 7:53 p.m. |
| NEDg | Description generation | batch_6a0385d8a43c8190b61222b65c1f9a60 |
completed | May 12, 2026, 7:56 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a03868a4898819083dc64e9d39b6c80 |
completed | May 12, 2026, 7:59 p.m. |
Created at: April 10, 2026, 10:29 a.m.