Triple
T15906281
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dr. Allison Mann |
E385728
|
entity |
| Predicate | creator |
P184
|
FINISHED |
| Object | Pia Guerra |
E385724
|
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: Pia Guerra | Statement: [Dr. Allison Mann, creator, Pia Guerra]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Pia Guerra Context triple: [Dr. Allison Mann, creator, Pia Guerra]
-
A.
Pia Guerra
chosen
Pia Guerra is a Canadian comic book artist best known for her acclaimed work on the Vertigo series "Y: The Last Man."
-
B.
Siparia
Siparia is a town in southern Trinidad known historically for its oil industry and its multicultural religious pilgrimage site, La Divina Pastora.
-
C.
Lola Valente
Lola Valente is a fictional character best known as the ambitious and talented protagonist of the Mexican teen telenovela "Lola, érase una vez."
-
D.
Andrea Guerra
Andrea Guerra is an Italian composer best known for his film scores, including his work on major international productions.
-
E.
Isabel Guzmán
Isabel Guzmán is an American government official who serves as the Administrator of the U.S. Small Business Administration, overseeing federal support for small businesses and entrepreneurs.
- 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_69d86da686e4819097cbf3b1fc2d881d |
completed | April 10, 2026, 3:25 a.m. |
| NER | Named-entity recognition | batch_69e1565b0d688190acc181c777387c65 |
completed | April 16, 2026, 9:36 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ffcf11fd1481909f460cfa4485d3e3 |
completed | May 10, 2026, 12:19 a.m. |
Created at: April 10, 2026, 4:52 a.m.