Triple
T30641910
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sebastian de Halleux |
E780003
|
entity |
| Predicate | playfishSpecialization |
P169649
|
FINISHED |
| Object | social network games |
—
|
LITERAL 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: social network games | Statement: [Sebastian de Halleux, playfishSpecialization, social network games]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: playfishSpecialization Context triple: [Sebastian de Halleux, playfishSpecialization, social network games]
-
A.
playsWithPick
Indicates that an entity engages in playing an instrument or object using a pick as the primary tool or accessory.
-
B.
playsWithHand
Indicates that an entity performs an action or engages in an activity using its hand.
-
C.
typicallyPlays
Indicates that an entity is most commonly or habitually associated with playing a particular role, instrument, position, or type of game.
-
D.
gameplayBasis
Indicates that one entity serves as the core mechanic, structure, or inspiration upon which another entity’s gameplay is designed or derived.
-
E.
playsSevensVariant
Indicates that an entity participates in or engages in a sevens variant of a game or sport.
- 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_69f224a50ebc81909b961a94c7f66b12 |
completed | April 29, 2026, 3:32 p.m. |
| NER | Named-entity recognition | batch_69f68a564ff08190940e6580ec2a0ef6 |
completed | May 2, 2026, 11:35 p.m. |
| PD | Predicate disambiguation | batch_69f67e448a9c8190b591374d98799fe3 |
completed | May 2, 2026, 10:44 p.m. |
| PDg | Predicate description generation | batch_69f67f0353c88190a05b2db449abe0f4 |
completed | May 2, 2026, 10:47 p.m. |
Created at: April 29, 2026, 8:29 p.m.