Triple
T16291802
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tad Martin |
E395540
|
entity |
| Predicate | stepChild |
P11545
|
FINISHED |
| Object |
Marissa Tasker
Marissa Tasker is a fictional character from the soap opera "All My Children," known for her complex family ties and dramatic storylines in Pine Valley.
|
E1375764
|
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: Marissa Tasker | Statement: [Tad Martin, stepChild, Marissa Tasker]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Marissa Tasker Context triple: [Tad Martin, stepChild, Marissa Tasker]
-
A.
Marissa Paternoster
Marissa Paternoster is an American guitarist, singer, and songwriter best known as the frontwoman of the punk band Screaming Females.
-
B.
Marissa Wilson
Marissa Wilson is the retired spy-turned-mother protagonist in the family action film "Spy Kids: All the Time in the World."
-
C.
Julie Hickson
Julie Hickson is a film producer best known for her work on Tim Burton’s early short film "Frankenweenie" (1984).
-
D.
Alissa McKersie
Alissa McKersie is a science fiction fan and fanzine editor known for her work on the Hugo Award-winning fanzine Journey Planet.
-
E.
Allison Feaster
Allison Feaster is a former American professional basketball player best known for her standout WNBA career and later work as an NBA front office executive.
- 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: Marissa Tasker Triple: [Tad Martin, stepChild, Marissa Tasker]
Generated description
Marissa Tasker is a fictional character from the soap opera "All My Children," known for her complex family ties and dramatic storylines in Pine Valley.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Marissa Tasker Target entity description: Marissa Tasker is a fictional character from the soap opera "All My Children," known for her complex family ties and dramatic storylines in Pine Valley.
-
A.
Marissa Paternoster
Marissa Paternoster is an American guitarist, singer, and songwriter best known as the frontwoman of the punk band Screaming Females.
-
B.
Marissa Wilson
Marissa Wilson is the retired spy-turned-mother protagonist in the family action film "Spy Kids: All the Time in the World."
-
C.
Julie Hickson
Julie Hickson is a film producer best known for her work on Tim Burton’s early short film "Frankenweenie" (1984).
-
D.
Alissa McKersie
Alissa McKersie is a science fiction fan and fanzine editor known for her work on the Hugo Award-winning fanzine Journey Planet.
-
E.
Allison Feaster
Allison Feaster is a former American professional basketball player best known for her standout WNBA career and later work as an NBA front office executive.
- 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_69d87f22c7248190a54c949738441e2e |
completed | April 10, 2026, 4:40 a.m. |
| NER | Named-entity recognition | batch_69e24919345881909ba4e7fe2e59340f |
completed | April 17, 2026, 2:52 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0733b28b808190a06ec86a6e2adb83 |
completed | May 15, 2026, 2:54 p.m. |
| NEDg | Description generation | batch_6a073623e5a08190a5a7398ee9bc56b2 |
completed | May 15, 2026, 3:05 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a073712f4048190831dddd875e82324 |
completed | May 15, 2026, 3:09 p.m. |
Created at: April 10, 2026, 5:05 a.m.