Triple
T31947347
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Laura Bailey as Abby Anderson |
E815686
|
entity |
| Predicate | gameWriter |
P173037
|
FINISHED |
| Object | Neil Druckmann |
—
|
NE NERFINISHED |
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: Neil Druckmann | Statement: [Laura Bailey as Abby Anderson, gameWriter, Neil Druckmann]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: gameWriter Context triple: [Laura Bailey as Abby Anderson, gameWriter, Neil Druckmann]
-
A.
dialogueWriter
Indicates that an entity is responsible for writing or creating dialogue for another entity, work, or context.
-
B.
storyEngine
Indicates that one entity functions as a narrative-generating or plot-controlling mechanism for another entity or set of events.
-
C.
gameEngine
Indicates that one entity serves as the game engine or core runtime system used to develop, run, or power another entity (such as a game or interactive application).
-
D.
scriptWriter
Indicates that one entity is the person who wrote or authored the script associated with another entity.
-
E.
gameProducer
Indicates that one entity is the producer responsible for creating, managing, or overseeing the development of a game associated with another entity.
- F. None of above. chosen
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_69f348f42d188190a33fc8d20ec50517 |
completed | April 30, 2026, 12:20 p.m. |
| NER | Named-entity recognition | batch_69f6b2d9aad88190a445f8f591cb19fc |
completed | May 3, 2026, 2:28 a.m. |
| PD | Predicate disambiguation | batch_69f6b14faf608190a25b977c0740729c |
completed | May 3, 2026, 2:22 a.m. |
| PDg | Predicate description generation | batch_69f6b21da77081908c5c015c4606d344 |
completed | May 3, 2026, 2:25 a.m. |
Created at: May 1, 2026, 12:07 a.m.